Title of Invention

METHOD AND APPARATUS FOR SIGNAL PROCESSING

Abstract An indication of the loudness of an audio signal containing speech and other types of audio material is obtained by classifying (12) segments of audio information as either speech or non-speech. The loudness of the speech segments is estimated (14) and this estimate is used to derive the indication of loudness. The indication of loudness may be used to control audio signal levels so that variations in loudness of speech between different programs is reduced. A preferred method for classifying speech segments is described.
Full Text DESCRIPTION
TECHNICAL FIELD
The present invention is related to audio systems and methods that are concerned with
the measuring and controlling of the loudness of speech in audio signals that contain speech
and other types of audio material.
BACKGROUND ART
While listening to radio or television broadcasts, listeners frequently choose a volume
control setting to obtain a satisfactory loudness of speech. The desired volume control setting
is influenced by a number of factors such as ambient noise in the listening environment,
frequency response of the reproducing system, and personal preference. After choosing the
volume control setting, the listener generally desires the loudness of speech to remain
relatively constant despite the presence or absence of other program materials such as music or
sound effects.
When the program changes or a different channel is selected, the loudness of speech in
the new program is often different, which requires changing the volume control setting to
restore the desired loudness. Usually only a modest change in the setting, if any, is needed to
adjust the loudness of speech in programs delivered by analog broadcasting techniques because
most analog broadcasters deliver programs with speech near the maximum allowed level that
may be conveyed by the analog broadcasting system. This is generally done by compressing
the dynamic range of the audio program material to raise the speech signal level relative to the
noise introduced by various components in the broadcast system. Nevertheless, there still are
undesirable differences in the loudness of speech for programs received on different channels
and for different types of programs received on the same channel such as commercial
announcements or "commercials" and the programs they interrupt.
The introduction of digital broadcasting techniques will likely aggravate this problem
because digital broadcasters can deliver signals with an adequate signal-to-noise level without
compressing dynamic range and without setting the level of speech near the maximum allowed
level. As a result, it is very likely there will be much greater differences in the loudness of
speech between different programs on the same channel and between programs from different

channels. For example, it has been observed that the difference in the level of speech between
programs received from analog and digital television channels sometimes exceeds 20 dB.
One way in which this difference in loudness can be reduced is for all digital
broadcasters to set the level of speech to a standardized loudness that is well below the
maximum level, which would allow enough headroom for wide dynamic range material to
avoid the need for compression or limiting. Unfortunately, this solution would require a change
in broadcasting practice that is unlikely to happen.
Another solution is provided by the AC-3 audio coding technique adopted for digital
television broadcasting in the United States. A digital broadcast that complies with the AC-3
standard conveys metadata along with encoded audio data. The metadata includes control
information known as "dialnorm" that can be used to adjust the signal level at the receiver to
provide uniform or normalized loudness of speech. In other words, the dialnorm information
allows a receiver to do automatically what the listener would have to do otherwise, adjusting
volume appropriately for each program or channel. The listener adjusts the volume control
setting to achieve a desired level of speech loudness for a particular program and the receiver
uses the dialnorm information to ensure the desired level is maintained despite differences that
would otherwise exist between different programs or channels. Additional information
describing the use of dialnorm information can be obtained from the Advanced Television
Systems Committee (ATSC) A/52A document entitled "Revision A to Digital Audio
Compression (AC-3) Standard" published August 20, 2001, and from the ATSC document
A/54 entitled "Guide to the Use of the ATSC Digital Television Standard" published October
4, 1995.
The appropriate value of dialnorm must be available to the part of the coding system
that generates the AC-3 compliant encoded signal. The encoding process needs a way to
measure or assess the loudness of speech in a particular program to determine the value of
dialnorm that can be used to maintain the loudness of speech in the program that emerges from
the receiver.
The loudness of speech can be estimated in a variety of ways. Standard TEC 60804
(2000-10) entitled "Integrating-averaging sound level meters" published by the International
Electrotechnical Commission (DEC) describes a measurement based on frequency-weighted
and time-averaged sound-pressure levels. ISO standard 532:1975 entitled "Method for
calculating loudness level" published by the International Organization for Standardization
describes methods that obtain a measure of loudness from a combination of power levels

calculated for frequency subbands. Examples of psychoacoustic models that may be used to
estimate loudness are described in Moore, Glasberg and Baer, "A model for the prediction of
thresholds, loudness and partial loudness," J. Audio Eng. Soc, vol. 45, no. 4, April 1997, and
in Glasberg and Moore, "A model of loudness applicable to time-varying sounds," J. Audio
Eng. Soc, vol. 50, no. 5, May 2002.
Unfortunately, there is no convenient way to apply these and other known techniques.
In broadcast applications, for example, the broadcaster is obligated to select an interval of
audio material, measure or estimate the loudness of speech in the selected interval, and transfer
the measurement to equipment that inserts the dialnorm information into the AC-3 compliant
digital data stream. The selected interval should contain representative speech but not contain
other types of audio material that would distort the loudness measurement. It is generally not
acceptable to measure the overall loudness of an audio program because the program includes
other components that are deliberately louder or quieter than speech. It is often desirable for
the louder passages of music and sound effects to be significantly louder than the preferred
speech level. It is also apparent that it is very undesirable for background sound effects such as
wind, distant traffic, or gently flowing water to have the same loudness as speech.
The inventors have recognized that a technique for determining whether an audio signal
contains speech can be used in an improved process to establish an appropriate value for the
dialnorm information. Any one of a variety of techniques for speech detection can be used. A
few techniques are described in the references cited below.
US patent 4,281,218, issued July 28, 1981, describes a technique that classifies a signal
as either speech or non-speech by extracting one or more features of the signal such as short-
term power. The classification is used to select the appropriate signal processing methodology
for speech and non-speech signals.
US patent 5,097,510, issued March 17, 1992, describes a technique that analyzes
variations in the input signal amplitude envelope. Rapidly changing variations are deemed to
be speech, which are filtered out of the signal. The residual is classified into one of four classes
of noise and the classification is used to select a different type of noise-reduction filtering for
the input signal.
US patent 5,457,769, issued October 10, 1995, describes a technique for detecting
speech to operate a voice-operated switch. Speech is detected by identifying signals that have
component frequencies separated from one another by about 150 Hz. This condition indicates
it is likely the signal conveys formants of speech.

EP patent application publication 0 737 Oil, published for grant October 14, 1009, and
US patent 5,878,391, issued March 2, 1999, describe a technique that generates a signal
representing a probability that an audio signal is a speech signal. The probability is derived by
extracting one or more features from the signal such as changes in power ratios between
different portions of the spectrum. These references indicate the reliability of the derived
probability can be improved if a larger number of features are used for the derivation.
US patent 6,061,647, issued May 9, 2000, discloses a technique for detecting speech by
storing a model of noise without speech, comparing an input signal to the model to decide
whether speech is present, and using an auxiliary detector to decide when the input signal can
be used to update the noise model.
International patent application publication WO 98/27543, published June 25, 1998,
discloses a technique that discerns speech from music by extracting a set of features from an
input signal and using one of several classification techniques for each feature. The best set of
features and the appropriate classification technique to use for each feature is determined
empirically.
The techniques disclosed in these references and all other known speech-detection
techniques attempt to detect speech or classify audio signals so that the speech can be
processed or manipulated by a method that differs from the method used to process or
manipulate non-speech signals.
US patent 5,819,247, issued October 6, 1998, discloses a technique for constructing a
hypothesis to be used in classification devices such as optical character recognition devices.
Weak hypotheses are constructed from examples and then evaluated. An iterative process
constructs stronger hypotheses for the weakest hypotheses. Speech detection is not mentioned
but the inventors have recognized that this technique may be used to improve known speech
detection techniques.
DISCLOSURE OF INVENTION
It is an object of the present invention to provide for a control of the loudness of speech
in signals that contain speech and other types of audio material.
According to the present invention, a signal is processed by receiving an input signal
and obtaining audio information from the input signal that represents an interval of an audio
signal, examining the audio information to classify segments of the audio information as being
either speech segments or non-speech segments, examining the audio information to obtain an

estimated loudness of the speech segments, and providing an indication of the loudness of the
interval of the audio signal by generating control information that is more responsive to the
estimated loudness of the speech segments than to the loudness of the portions of the audio
signal represented by the non-speech segments.
The indication of loudness may be used to control the loudness of the audio signal to
reduce variations in the loudness of the speech segments. The loudness of the portions of the
audio signal represented by non-speech segments is increased when the loudness of the
portions of the audio signal represented by the speech-segments is increased.
The various features of the present invention and its preferred embodiments may be
better understood by referring to the following discussion and the accompanying drawings in
which like reference numerals refer to like elements in the several figures. The contents of the
following discussion and the drawings are set forth as examples only and should not be
understood to represent limitations upon the scope of the present invention.
BRIEF DESCRIPTION OF ACCOMPANYING DRAWINGS
Fig. 1 is a schematic block diagram of an audio system that may incorporate various
aspects of the present invention.
Fig. 2 is a schematic block diagram of an apparatus that may be used to control
loudness of an audio signal containing speech and other types of audio material.
Fig. 3 is a schematic block diagram of an apparatus that may be used to generate and
transmit audio information representing an audio signal and control information representing
loudness of speech.
Fig. 4 is a schematic block diagram of an apparatus that may be used to provide an
indication of loudness for speech in an audio signal containing speech and other types of audio
material.
Fig. 5 is a schematic block diagram of an apparatus that may be used to classify
segments of audio information.
Fig. 6 is a schematic block diagram of an apparatus that may be used to implement
various aspects of the present invention.
MODES FOR CARRYING OUT THE INVENTION
A. System Overview
Fig. 1 is a schematic block diagram of an audio system in which the transmitter 2
receives an audio signal from the path 1, processes the audio signal to generate audio

information representing the audio signal, and transmits the audio information along the path 3.
The path 3 may represent a communication path that conveys the audio information for
immediate use, or it may represent a signal path coupled to a storage medium that stores the
audio information for subsequent retrieval and use. The receiver 4 receives the audio
information from the path 3, processes the audio information to generate an audio signal, and
transmits the audio signal along the path S for presentation to a listener.
The system shown in Fig. 1 includes a single transmitter and receiver; however, the
present invention may be used in systems that include multiple transmitters and/or multiple
receivers. Various aspects of the present invention may be implemented in only the transmitter
2, in only the receiver 4, or in both the transmitter 2 and the receiver 4.
In one implementation, the transmitter 2 performs processing that encodes the audio
signal into encoded audio information that has lower information capacity requirements than
the audio signal so that the audio information can be transmitted over channels having a lower
bandwidth or stored by media having less space. The decoder 4 performs processing that
decodes the encoded audio information into a form that can be used to generate an audio signal
that preferably is perceptually similar or identical to the input audio signal. For example, the
transmitter 2 and the receiver 4 may encode and decode digital bit streams compliant with the
AC-3 coding standard or any of several standards published by the Motion Picture Experts
Group (MPEG). The present invention may be applied advantageously in systems that apply
encoding and decoding processes; however, these processes are not required to practice the
present invention.
Although the present invention may be implemented by analog signal processing
techniques, implementation by digital signal processing techniques is usually more convenient.
The following examples refer more particularly to digital signal processing.
B. Speech Loudness
The present invention is directed toward controlling the loudness of speech in signals
that contain speech and other types of audio material. The entries in Tables I and III represent
sound levels for various types of audio material in different programs.
Table I includes information for the relative loudness of speech in three programs like
those that may be broadcast to television receivers. In Newscast 1, two people are speaking at
different levels. In Newscast 2, a person is speaking at a low level at a location with other
sounds that are occasionally louder than the speech. Music is sometimes present at a low level.
In Commercial, a person is speaking at a very high level and music is occasionally even louder.


The present invention allows an audio system to automatically control the loudness of
the audio material in the three programs so that variations in the loudness of speech is reduced
automatically. The loudness of the audio material in Newscast 1 can also be controlled so that
differences between levels of the two voices is reduced. For example, if the desired level for all
speech is -24 dB, then the loudness of the audio material shown in Table I could be adjusted to
the levels shown in Table II.

Table III includes information for the relative loudness of different sounds in three
different scenes of one or more motion pictures. In Scene 1, people are speaking on the deck of
a ship. Background sounds include the lapping of waves and a distant fog horn at levels
significantly below the speech level. The scene also includes a blast from the ship's horn,
which is substantially louder than the speech. In Scene 2, people are whispering and a clock is
ticking in the background. The voices in this scene are not as loud as normal speech and the
loudness of the clock ticks is even lower. In Scene 3, people are shouting near a machine that is
making an even louder sound. The shouting is louder than normal speech.


The present invention allows an audio system to automatically control the loudness of
the audio material in the three scenes so that variations in the loudness of speech is reduced.
For example, the loudness of the audio material could be adjusted so that the loudness of
speech in all of the scenes is the same or essentially the same.
Alternatively, the loudness of the audio material can be adjusted so that the speech
loudness is within a specified interval. For example, if the specified interval of speech loudness
is from -24 dB to -30 dB, the levels of the audio material shown in Table III could be adjusted
to the levels shown in Table IV.

In another implementation, the audio signal level is controlled so that some average of
the estimated loudness is maintained at a desired level. The average may be obtained for a
specified interval such as ten minutes, or for all or some specified portion of a program.
Referring again to the loudness information shown in Table III, suppose the three scenes are in
the same motion picture, an average loudness of speech for the entire motion picture is
estimated to be at -25 dB, and the desired loudness of speech is -27 dB. Signal levels for the
three scenes are controlled so that the estimated loudness for each scene is modified as shown
in Table V. In this implementation, variations of speech loudness within the program or motion
picture are preserved but variations with the average loudness of speech in other programs or
motion pictures is reduced. In other words, variations in the loudness of speech between
programs or portions of programs can be achieved without requiring dynamic range
compression within those programs or portions of programs.


Compression of the dynamic range may also be desirable; however, this feature is
optional and may be provided when desired.
C. Controlling Speech Loudness
The present invention may be carried out by a stand-alone process performed within
either a transmitter or a receiver, or by cooperative processes performed jointly within a
transmitter and receiver.
1. Stand-alone Process
Fig. 2 is a schematic block diagram of an apparatus that may be used to implement a
stand-alone process in a transmitter or a receiver. The apparatus receives from the path 11
audio information that represents an interval of an audio signal. The classifier 12 examines the
audio information and classifies segments of the audio information as being "speech segments"
that represent portions of the audio signal that are classified as speech, or as being "non-speech
segments" that represent portions of the audio signal that are not classified as speech. The
classifier 12 may also classify the non-speech segments into a number of classifications.
Techniques that may be used to classify segments of audio information are mentioned above.
A preferred technique is described below.
Each portion of the audio signal that is represented by a segment of audio information
has a respective loudness. The loudness estimator 14 examines the speech segments and
obtains an estimate of this loudness for the speech segments. An indication of the estimated
loudness is passed along the path 15. In an alternative implementation, the loudness estimator
14 also examines at least some of the non-speech segments and obtains an estimated loudness
for these segments. Some ways in which loudness may be estimated are mentioned above.
The controller 16 receives the indication of loudness from the path 15, receives the
audio information from the path 11, and modifies the audio information as necessary to reduce
variations in the loudness of the portions of the audio signal represented by speech segments. If
the controller 16 increases the loudness of the speech segments, then it will also increase the
loudness of all non-speech segments including those that are even louder than the speech
segments. The modified audio information is passed along the path 17 for subsequent
processing. In a transmitter, for example, the modified audio information can be encoded or
otherwise prepared for transmission or storage. In a receiver, the modified audio information
can be processed for presentation to a listener.
The classifier 12, the loudness estimator 14 and the controller 16 are arranged in such a
manner that the estimated loudness of the speech segments is used to control the loudness of

the non-speech segments as well as the speech segments. This may be done in a variety of
ways. In one implementation, the loudness estimator 14 provides an estimated loudness for
each speech segment. The controller 16 uses the estimated loudness to make any needed
adjustments to the loudness of the speech segment for which the loudness was estimated, and it
uses this same estimate to make any needed adjustments to the loudness of subsequent non-
speech segments until a new estimate is received for the next speech segment. This
implementation is appropriate when signal levels must be adjusted in real time for audio
signals that cannot be examined in advance. In another implementation that may be more
suitable when an audio signal can be examined in advance, an average loudness for the speech
segments in all or a large portion of a program is estimated and that estimate is used to make
any needed adjustment to the audio signal. In yet another implementation, the estimated level
is adapted in response to one or more characteristics of the speech and the non-speech
segments of audio information, which may be provided by the classifier 12 through the path
shown by a broken line.
In a preferred implementation, the controller 16 also receives an indication of loudness
or signal energy for all segments and makes adjustments in loudness only within segments
having a loudness or an energy level below some threshold. Alternatively, the classifier 12 or
the loudness estimator 14 can provide to the controller 16 an indication of the segments within
which an adjustment to loudness may be made.
2. Cooperative Process
Fig. 3 is a schematic block diagram of an apparatus that may be used to implement part
of a cooperative process in a transmitter. The transmitter receives from the path 11 audio
information that represents an interval of an audio signal. The classifier 12 and the loudness
estimator 14 operate substantially the same as that described above. An indication of the
estimated loudness provided by the loudness estimator 14 is passed along path 15. In the
implementation shown in the figure, the encoder 18 generates along the path 19 an encoded
representation of the audio information received from the path 11. The encoder 18 may apply
essentially any type of encoding that may be desired including so called perceptual coding. For
example, the apparatus illustrated in Fig. 3 can be incorporated into an audio encoder to
provide dialnorm information for assembly into an AC-3 compliant data stream. The encoder
18 is not essential to the present invention. In an alternative implementation that omits the
encoder 18, the audio information itself is passed along path 19. The formatter 20 assembles
the representation of the audio information received from the path 19 and the indication of

estimated loudness received from the path 15 into an output signal, which is passed along the
path 21 for transmission or storage.
In a complementary receiver that is not shown in any figure, the signal generated along
path 21 is received and processed to extract the representation of the audio information and the
indication of estimated loudness. The indication of estimated loudness is used to control the
signal levels of an audio signal that is generated from the representation of the audio
information.
3. Loudness Meter
Fig. 4 is a schematic block diagram of an apparatus that may be used to provide an
indication of speech loudness for speech in an audio signal containing speech and other types
of audio material. The apparatus receives from the path 11 audio information that represents an
interval of an audio signal. The classifier 12 and the loudness estimator 14 operate
substantially the same as that described above. An indication of the estimated loudness
provided by the loudness estimator 14 is passed along the path 15. This indication may be
displayed in any desired form, or it may be provided to another device for subsequent
processing.
D. Segment Classification
The present invention may use essentially any technique that can classify segments of
audio information into two or more classifications including a speech classification. Several
examples of suitable classification techniques are mentioned above. In a preferred
implementation, segments of audio information are classified using some form of the technique
that is described below.
Fig. 5 is a schematic block diagram of an apparatus that may be used to classify
segments of audio information according to the preferred classification technique. The sample-
rate converter receives digital samples of audio information from the path 11 and re-samples
the audio information as necessary to obtain digital samples at a specified rate. In the
implementation described below, the specified rate is 16 k samples per second. Sample rate
conversion is not required to practice the present invention; however, it is usually desirable to
convert the audio information sample rate when the input sample rate is higher than is needed
to classify the audio information and a lower sample rate allows the classification process to be
performed more efficiently. In addition, the implementation of the components that extract the
features can usually be simplified if each component is designed to work with only one sample
rate.

In the implementation shown, three features or characteristics of the audio information
are extracted by extraction components 31, 32 and 33. In alternative implementations, as few
as one feature or as many features that can be handled by available processing resources may
be extracted. The speech detector 35 receives the extracted features and uses them to determine
whether a segment of audio information should be classified as speech. Feature extraction and
speech detection are discussed below.
1. Features
In the particular implementation shown in Fig. S, components are shown that extract
only three features from the audio information for illustrative convenience. In a preferred
implementation, however, segment classification is based on seven features that are described
below. Each extraction component extracts a feature of the audio information by performing
calculations on blocks of samples arranged in frames. The block size and the number of blocks
per frame that are used for each of seven specific features are shown in Table VI.

In this implementation, each frame is 32,768 samples or about 2.057 seconds in length.
Each of the seven features that are shown in the table is described below. Throughout the
following description, the number of samples in a block is denoted by the symbol N and the
number of blocks per frame is denoted by the symbol M.

a) Average squared l2-norm of weighted spectral flux
The average squared l2-norm of the weighted spectral flux exploits the fact that speech
normally has a rapidly varying spectrum. Speech signals usually have one of two forms: a
tone-like signal referred to as voiced speech, or a noise-like signal referred to as unvoiced
speech. A transition between these two forms causes abrupt changes in the spectrum.
Furthermore, during periods of voiced speech, most speakers alter the pitch for emphasis, for
lingual stylization, or because such changes are a natural part of the language. Non-speech
signals like music can also have rapid spectral changes but these changes are usually less
frequent. Even vocal segments of music have less frequent changes because a singer will
usually sing at the same frequency for some appreciable period of time.
The first step in one process that calculates the average squared l2-norm of the
weighted spectral flux applies a transform such as the Discrete Fourier Transform (DFT) to a
block of audio information samples and obtains the magnitude of the resulting transform
coefficients. Preferably, the block of samples are weighted by a window function w[n] such as
a Hamming window function prior to application of the transform. The magnitude of the DFT
coefficients may be calculated as shown in the following equation.

where N= the number of samples in a block;
x[n] = sample number n in block m; and
Xm[k] = transform coefficient k for the samples in block m.
The next step calculates a weight W for the current block from the average power of the
current and previous blocks. Using Parseval's theorem, the average power can be calculated
from the transform coefficients as shown in the following equation if samples x[n] have real
rather than complex or imaginary values.

where Wm = the weight for the current block m.
The next step squares the magnitude of the difference between the spectral components
of the current and previous blocks and divides the result by the block weight Wm of the current
block, which is calculated according to equation 2, to yield a weighted spectral flux. The l2-

norm or the Euclidean distance is then calculated. The weighted spectral flux and the l2-norm
calculations are shown in the following equation.

The feature for a frame of blocks is obtained by calculating the sum of the squared l2-
norms for each of the blocks in the frame. This summation is shown in the following equation.

F1(t) = the feature for average squared /2-norm of the weighted spectral flux for frame
t.
b) Skew of regressive line of best fit through estimated spectral power density
The gradient or slope of the regressive line of best fit through the log spectral power
density gives an estimate of the spectral tilt or spectral emphasis of a signal. If a signal
emphasizes lower frequencies, a line that approximates the spectral shape of the signal tilts
downward toward the higher frequencies and the slope of the line is negative. If a signal
emphasizes higher frequencies, a line that approximates the spectral shape of the signal tilts
upward toward higher frequencies and the slope of the line is positive.
Speech emphasizes lower frequencies during intervals of voiced speech and emphasizes
higher frequencies during intervals of unvoiced speech. The slope of a line approximating the
spectral shape of voiced speech is negative and the slope of a line approximating the spectral
shape of unvoiced speech is positive. Because speech is predominantly voiced rather than
unvoiced, the slope of a line that approximates the spectral shape of speech should be negative
most of the time but rapidly switch between positive and negative slopes. As a result, the
distribution of the slope or gradient of the line should be strongly skewed toward negative
values. For music and other types of audio material the distribution of the slope is more
symmetrical.
A line that approximates the spectral shape of a signal may be obtained by calculating a
regressive line of best fit through the log spectral power density estimate of the signal. The
spectral power density of the signal may be obtained by calculating the square of transform

coefficients using a transform such as that shown above in equation 1. The calculation for
spectral power density is shown in the following equation.

The power spectral density calculated in equation 5 is then converted into the log-
domain as shown in the following equation.

The gradient of the regressive line of best fit is then calculated as shown in the
following equation, which is derived from the method of least squares.

where Gm = the regressive coefficient for block m.
The feature for frame t is the estimate of the skew over the frame as given in the
following equation.

where F2(t) = the feature for gradient of the regressive line of best fit through the log spectral
power density for frame t.
c) Pause count
The pause count feature exploits the fact that pauses or short intervals of signal with
little or no audio power are usually present in speech but other types of audio material usually
do not have such pauses.
The first step for feature extraction calculates the power P[m] of the audio information
in each block m within a frame. This may be done as shown in the following equation.

where P[m] = the calculated power in block m.

The second step calculates the power PF of the audio information within the frame. The
feature for the number of pauses F3(t) within frame / is equal to the number of blocks within
the frame whose respective power P[m] is less than or equal to ¼PF. The value of one-quarter
was derived empirically.
d) Skew coefficient of zero crossing rate
The zero crossing rate is the number of times the audio signal, which is represented by
the audio information, crosses through zero in an interval of time. The zero crossing rate can be
estimated from a count of the number of zero crossings in a short block of audio information
samples. In the implementation described here, the blocks have a duration of 256 samples for
16 msec.
Although simple in concept, information derived from the zero crossing rate can
provide a fairly reliable indication of whether speech is present in an audio signal. Voiced
portions of speech have a relatively low zero crossings rate, while unvoiced portions of speech
have a relatively high zero crossing rate. Furthermore because speech typically contains more
voiced portions and pauses than unvoiced portions, the distribution of zero crossing rates is
generally skewed toward lower rates. One feature that can provide an indication of the skew
within a frame t is a skew coefficient of the zero crossing rate that can be calculated from the
following equation.

where Zm - the zero crossing count in block m, and
F4(t) = the feature for skew coefficient of the zero crossing rate for frame t.
e) Mean-to-median ratio of zero crossing rate
Another feature that can provide an indication of the distribution skew of the zero
crossing rates within a frame / is the median-to-mean ratio of the zero crossing rate. This can
be obtained from the following equation.

where Zmedion = the median of the block zero crossing rates for all blocks in frame /; and

F5(t) = the feature for median-to-mean ratio of the zero crossing rate for frame t.
f) Short Rhythmic measure
Techniques that use the previously described features can detect speech in many types
of audio material; however, these techniques will often make false detections in highly
rhythmic audio material like so called "rap" and many instances of pop music. Segments of
audio information can be classified as speech more reliably by detecting highly rhythmic
material and either removing such material from classification or raising the confidence level
required to classify the material as speech.
The short rhythmic measure may be calculated for a frame by first calculating the
variance of the samples in each block as shown in the following equation.

where σ2x[m] = the variance of the samples x in block m\ and
xm .= the mean of the samples x in block m.
A zero-mean sequence is derived from the variances for all of the blocks in the frame as
shown in the following equation.

where δ[m] = the element in the zero-mean sequence for block m; and
σ2x = the mean of the variances for all blocks in the frame.
The autocorrelation of the zero-mean sequence is obtained as shown in the following
equation.

where At[ℓ ] = the autocorrelation value for frame t with a block lag of I.
The feature for the short rhythmic measure is derived from a maximum value of the
autocorrelation scores. This maximum score does not include the score for a block lag ℓ=0, so
the maximum value is taken from the set of values for a block lag ℓ > L. The quantity L
represents the period of the most rapid rhythm expected. In one implementation L is set equal
to 10, which represents a minimum period of 160 msec. The feature is calculated as shown in
the following equation by dividing the maximum score by the autocorrelation score for the
block lag ℓ=0.


where F6(t) = the feature for short rhythmic measure for frame /.
g) Long rhythmic measure
The long rhythmic measure is derived in a similar manner to that described above for
the short rhythmic measure except the zero-mean sequence values are replaced by spectral
weights. These spectral weights are calculated by first obtaining the log power spectral density
as shown above in equations 5 and 6 and described in connection with the skew of the gradient
of the regressive line of best fit through the log spectral power density. It may be helpful to
point out that, in the implementation described here, the block length for calculating the long
rhythmic measure is not equal to the block length used for the skew-of-the-gradient
calculation.
The next step obtains the maximum log-domain power spectrum value for each block
as shown in the following equation.

where Om = the maximum log power spectrum value in block m.
A spectral weight for each block is determined by the number of peak log-domain
power spectral values that are greater than a threshold equal to (Om • α). This determination is
expressed in the following equation.

where W[m] = the spectral weight for block m;
sign(w) = +1 if n >0 and -1 if n α = an empirically derived constant equal to 0.1.
At the end of each frame, the sequence of M spectral weights from the previous frame
and the sequence of M spectral weights from the current frame are concatenated to form a
sequence of 2M spectral weights. An autocorrelation of this long sequence is then calculated
according to the following equation.

where ALt [ℓ] =the autocorrelation score for frame t.

The feature for the long rhythmic measure is derived from a maximum value of the
autocorrelation scores. This maximum score does not include the score for a block lag ℓ=0, so
the maximum value is taken from the set of values for a block lag ℓ>LL. The quantity LL.
represents the period of the most rapid rhythm expected. In the implementation described here,
LL is set equal to 10. The feature is calculated as shown in the following equation by dividing
the maximum score by the autocorrelation score for the block lag ℓ =0.

where F7(t) = the feature for the long rhythmic measure for frame /.
2. Speech Detection
The speech detector 35 combines the features that are extracted for each frame to
determine whether a segment of audio information should be classified as speech. One way
that may be used to combine the features implements a set of simple or interim classifiers. An
interim classifier calculates a binary value by comparing one of the features discussed above to
a threshold. This binary value is then weighted by a coefficient. Each interim classifier makes
an interim classification that is based on one feature. A particular feature may be used by more
than one interim classifier. An interim classifier may be implemented by calculations
performed according to the following equation.

where Cj = the binary-valued classification provided by interim classifier j;
cj = a coefficient for interim classifier j;
Fi= feature i extracted from the audio information; and
Thj = a threshold for interim classifierc j.
In this particular implementation, an interim classification Cj = 1 indicates the interim
classifier j tends to support a conclusion that a particular frame of audio information should be
classified as speech. An interim classification Cj = -1 indicates the interim classifier j tends to
support a conclusion that a particular frame of audio information should not be classified as
speech.
The entries in Table VII show coefficient and threshold values and the appropriate
feature for several interim classifiers that may be used in one implementation to classify frames
of audio information.


The final classification is based on a combination of the interim classifications. This
may be done as shown in the following equation.

where Cfinal = the final classification of a frame of audio information; and
J= the number of interim classifiers used to make the classification.
The reliability of the speech detector can be improved by optimizing the choice of
interim classifiers, and by optimizing the coefficients and thresholds for those interim
classifiers. This optimization may be carried out in a variety of ways including techniques
disclosed in US patent 5,819,247 cited above, and in Schapire, "A Brief Introduction to
Boosting," Proc. of the 16th Int. Joint Conf. on Artificial Intelligence, 1999.
In an alternative implementation, speech detection is not indicated by a binary-valued
decision but is, instead, represented by a graduated measure of classification. The measure
could represent an estimated probability of speech or a confidence level in the speech
classification. This may be done in a variety of ways such as, for example, obtaining the final

classification from a sum of the interim classifications rather than obtaining a binary-valued
result as shown in equation 21.
3. Sample Blocks
The implementation described above extracts features from contiguous, non-
overlapping blocks of fixed length. Alternatively, the classification technique may be applied
to contiguous non-overlapping variable-length blocks, to overlapping blocks of fixed or
variable length, or to non-contiguous blocks of fixed or varying length. For example, the block
length may be adapted in response to transients, pauses or intervals of little or no audio energy
so that the audio information in each block is more stationary. The frame lengths also may be
adapted by varying the number of blocks per frame and/or by varying the lengths of the blocks
within a frame.
E. Loudness Estimation
The loudness estimator 14 examines segments of audio information to obtain an
estimated loudness for the speech segments. In one implementation, loudness is estimated for
each frame that is classified as a segment of speech. The loudness may be estimated for
essentially any duration that is desired.
In another implementation, the estimating process begins in response to a request to
start the process and it continues until a request to stop the process is received. In the receiver
4, for example, these requests may be conveyed by special codes in the signal received from
the path 3. Alternatively, these requests may be provided by operation of a switch or other
control provided on the apparatus that is used to estimate loudness. An additional control may
be provided that causes the loudness estimator 14 to suspend processing and hold the current
estimate.
In one implementation, loudness is estimated for all segments of audio information that
are classified as speech. In principle, however, loudness could be estimated for only selected
speech segments such as, for example, only those segments having a level of audio energy
greater than a threshold. A similar effect also could be obtained by having the classifier 12
classify the low-energy segments as non-speech and then estimate loudness for all speech
segments. Other variations are possible. For example, older segments can be given less weight
in estimated loudness calculations.
In yet another alternative, the loudness estimator 14 estimates loudness for at least
some of the non-speech segments. The estimated loudness for non-speech segments may be
used in calculations of loudness for an interval of audio information; however, these

calculations should be more responsive to estimates for the speech segments. The estimates for
non-speech segments may also be used in implementations that provide a graduated measure of
classification for the segments. The calculations of loudness for an interval of the audio
information can be responsive to the estimated loudness for speech and non-speech segments
in a manner that accounts for the graduated measure of classification. For example, the
graduated measure may represent an indication of confidence that a segment of audio
information contains speech. The loudness estimates can be made more responsive to segments
with a higher level of confidence by giving these segments more weight in estimated loudness
calculations.
Loudness may be estimated in a variety of ways including those discussed above. No
particular estimation technique is critical to the present invention; however, it is believed that
simpler techniques that require fewer computational resources will usually be preferred in
practical implementations.
F. Implementation
Various aspects of the present invention may be implemented in a wide variety of ways
including software in a general-purpose computer system or in some other apparatus that
includes more specialized components such as digital signal processor (DSP) circuitry coupled
to components similar to those found in a general-purpose computer system. Fig. 6 is a block
diagram of device 70 that may be used to implement various aspects of the present invention in an
audio encoding transmitter or an audio decoding receiver. DSP 72 provides computing resources.
RAM 73 is system random access memory (RAM) used by DSP 72 for signal processing. ROM
74 represents some form of persistent storage such as read only memory (ROM) for storing
programs needed to operate device 70. I/O control 75 represents interface circuitry to receive and
transmit signals by way of communication channels 76, 77. Analog-to-digital converters and
digital-to-analog converters may be included in I/O control 75 as desired to receive and/or
transmit analog audio signals. In the embodiment shown, all major system components connect to
bus 71, which may represent more than one physical bus; however, a bus architecture is not
required to implement the present invention.
In embodiments implemented in a general purpose computer system, additional
components may be included for interfacing to devices such as a keyboard or mouse and a
display, and for controlling a storage device having a storage medium such as magnetic tape or
disk, or an optical medium. The storage medium may be used to record programs of instructions

for operating systems, utilities and applications, and may include embodiments of programs that
implement various aspects of the present invention.
The functions required to practice the present invention can also be performed by special
purpose components that are implemented in a wide variety of ways including discrete logic
components, one or more ASICs and/or program-controlled processors. The manner in which
these components are implemented is not important to the present invention.
Software implementations of the present invention may be conveyed by a variety machine
readable media such as baseband or modulated communication paths throughout the spectrum
including from supersonic to ultraviolet frequencies, or storage media including those that
convey information using essentially any magnetic or optical recording technology including
magnetic tape, magnetic disk, and optical disc. Various aspects can also be implemented in
various components of computer system 70 by processing circuitry such as ASICs, general-
purpose integrated circuits, microprocessors controlled by programs embodied in various forms of
ROM or RAM, and other techniques.

We claim:
1. A method for signal processing that comprises:
receiving an input signal and obtaining audio information from the input signal,wherein the
audio information represents an interval of an audio signal;
examining the audio information to classify segments of the audio information as being
speech segments representing portions of the audio signal classified as speech or as being non-
speech segments representing portions of the audio signal not classified as speech, wherein each
portion of the audio signal represented by a segment has a respective loudness, and the loudness of
the speech segments is less than the loudness of one or more loud non-speech segments;
examining the audio information to obtain an estimated loudness of the speech segments;
and
providing an indication of the loudness of the interval of the audio signal by generating
control information that is more responsive to the estimated loudness of the speech segments than
to the loudness of the portions of the audio signal represented by the non-speech segments.
2. The method as claimed in claim 1, that comprises:
controlling the loudness of the interval of the audio signal in response to the control
information so as to reduce variations in the loudness of the speech segments, wherein the loudness
of the portions of the audio signal represented by the one or more loud non-speech segments is
increased when the loudness of the portions of the audio signal represented by the speech-segments
is increased.
3. The method as claimed in claim 1, that comprises:
assembling a representation of the audio information and the control information into an
output signal and transmitting the output signal.
4. The method as claimed in claim 1 or 2, that obtains the estimated loudness of the speech
segments by calculating average power of a frequency-weighted version of the audio signal
represented by the speech segments.
5. The method as claimed in claim 1 or 2, that obtains the estimated loudness of the speech
segments by applying a psychoacoustic model of loudness to the audio information.

6. The method as claimed in claim 1 or 2, that classifies segments by deriving from the audio
information a plurality of characteristics of the audio signal, weighting each characteristic by a
respective measure of importance, and classifying the segments according to a combination of the
weighted characteristics.
7. The method as claimed in claim 1 or 2, that controls the loudness of the interval of the audio
signal by adjusting the loudness only during intervals of the audio signal having a measure of audio
energy less than a threshold.
8. The method as claimed in claim 1 or 2, wherein the indication of the loudness of the interval
of the audio signal is responsive only to the estimated loudness of the speech segments.
9. The method as claimed in claim 1 or 2, that comprises estimating the loudness of one or
more non-speech segments, wherein the indication of the loudness of the interval of the audio signal
is more responsive to the estimated loudness of the speech segments than to the estimated loudness
of the one or more non-speech segments.
10. The method as claimed in claim 1 or 2, that comprises:
providing a speech measure that indicates a degree to which the audio signal represented by
a respective segment has characteristics of speech; and
providing the indication of loudness such that it is responsive to the estimated loudness of
respective segments according to the speech measures of the respective segments.
11. The method as claimed in claim 1 or 2, that comprises providing the indication of loudness
such that it is responsive to the estimated loudness of respective segments according to time order
of the segments.
12. The method as claimed in claim 1 or 2, that comprises adapting lengths of the segments of
audio information in response to characteristics of the audio information.
13. The method as claimed in claim 1 or 2, wherein the indication of the loudness is not
responsive to the loudness of the portions of the audio signal represented by the non-speech
segments.

14. The method as claimed in claim 1 or 2, wherein the examining of the audio information
obtains estimates of the respective loudness of the speech segments.
15. The method as claimed in claim 2, wherein the loudness of the interval of the audio signal is
controlled using a respective estimated loudness for the speech segment for which the respective
estimated loudness was obtained as well as subsequent non-speech segments until another estimated
loudness is obtained for another speech segment.
16. The method as claimed in claim 2, wherein the loudness of the interval of the audio signal is
controlled using an estimate of average loudness for the speech segments.
17. The method as claimed in claim 2, wherein the loudness of the interval of the audio signal is
controlled for only those segments having a loudness or energy level below a threshold.
18. An apparatus for signal processing that comprises:
an input terminal (76, 77) that receives an input signal;
memory (73, 74); and
processing circuitry (72, 75) coupled to the input terminal and the memory; wherein the
processing circuitry is adapted to:
receive an input signal and obtain audio information from the input signal, wherein the audio
information represents an interval of an audio signal;
examine the audio information to classify segments of the audio information as being speech
segments representing portions of the audio signal classified as speech or as being non-speech
segments representing portions of the audio signal not classified as speech, wherein each portion of
the audio signal represented by a segment has a respective loudness, and the loudness of the speech
segments is less than the loudness of one or more loud non-speech segments;
examine the audio information to obtain an estimated loudness of the speech segments; and
provide an indication of the loudness of the interval of the audio signal by generating control
information that is more responsive to the estimated loudness of the speech segments than to the
loudness of the portions of the audio signal represented by the non-speech segments.
19. The apparatus as claimed in claim 18, wherein the processing circuitry is adapted to control
the loudness of the interval of the audio signal in response to the control information so as to reduce
variations in the loudness of the speech segments, wherein the loudness of the portions of the audio

signal represented by the one or more loud non-speech segments is increased when the loudness of
the portions of the audio signal represented by the speech-segments is increased.
20. The apparatus as claimed in claim 18, wherein the processing circuitry is adapted to
assemble a representation of the audio information and the control information into an output signal
and transmit the output signal.
21. The apparatus as claimed in claim 18 or 19, wherein the processing circuitry is adapted to
obtain the estimated loudness of the speech segments by calculating average power of a frequency-
weighted version of the audio signal represented by the speech segments.
22. The apparatus as claimed in claim 18 or 19, wherein the processing circuitry is adapted to
obtain the estimated loudness of the speech segments by applying a psychoacoustic model of
loudness to the audio information.
23. The apparatus as claimed in claim 18 or 19, wherein the processing circuitry is adapted to
classify segments by deriving from the audio information a plurality of characteristics of the audio
signal, weight each characteristic by a respective measure of importance, and classify the segments
according to a combination of the weighted characteristics.
24. The apparatus as claimed in claim 18 or 19, wherein the processing circuitry is adapted to
control the loudness of the interval of the audio signal by adjusting the loudness only during
intervals of the audio signal having a measure of audio energy less than a threshold.
25. The apparatus as claimed in claim 18 or 19, wherein the indication of the loudness of the
interval of the audio signal is responsive only to the estimated loudness of the speech segments.
26. The apparatus as claimed in claim 18 or 19, wherein the processing circuitry is adapted to
estimate the loudness of one or more non-speech segments, wherein the indication of the loudness
of the interval of the audio signal is more responsive to the estimated loudness of the speech
segments than to the estimated loudness of the one or more non-speech segments.
27. The apparatus as claimed in claim 18 or 19, wherein the processing circuitry is adapted to:
provide a speech measure that indicates a degree to which the audio signal represented by a
respective segment has characteristics of speech; and

provide the indication of loudness such that it is responsive to the estimated loudness of
respective segments according to the speech measures of the respective segments.
28. The apparatus as claimed in claim 18 or 19 wherein the processing circuitry is adapted to
provide the indication of loudness such that it is responsive to the estimated loudness of respective
segments according to time order of the segments.
29. The apparatus as claimed in claim 18 or 19 wherein the processing circuitry is adapted to
detect characteristics of the audio information and adapt lengths of the segments of audio
information in response to the detected characteristics.
30. The apparatus as claimed in claim 18 or 19, wherein the indication of the loudness is not
responsive to the loudness of the portions of the audio signal represented by the non-speech
segments.
31. The apparatus as claimed in claim 18 or 19, wherein the examining of the audio information
obtains estimates of the respective loudness of the speech segments.
32. The apparatus as claimed in claim 19, wherein the loudness of the interval of the audio
signal is controlled using a respective estimated loudness for the speech segment for which the
respective estimated loudness was obtained as well as subsequent non-speech segments until
another estimated loudness is obtained for another speech segment.
33. The apparatus as claimed in claim 19, wherein the loudness of the interval of the audio
signal is controlled using an estimate of average loudness for the speech segments.
34. The apparatus as claimed in claim 19, wherein the loudness of the interval of the audio
signal is controlled for only those segments having a loudness or energy level below a threshold.

Documents:

1936-KOLNP-2004-ABSTRACT-1.1.pdf

1936-kolnp-2004-abstract.pdf

1936-KOLNP-2004-AMANDED CLAIMS.pdf

1936-kolnp-2004-assignment.pdf

1936-kolnp-2004-assignment1.1.pdf

1936-KOLNP-2004-CANCELLED PAGES.pdf

1936-kolnp-2004-claims.pdf

1936-kolnp-2004-correspondence.pdf

1936-kolnp-2004-correspondence1.1.pdf

1936-KOLNP-2004-DESCRIPTION (COMPLETE)-1.1.pdf

1936-kolnp-2004-description (complete).pdf

1936-kolnp-2004-drawings.pdf

1936-kolnp-2004-examination report.pdf

1936-kolnp-2004-form 1.pdf

1936-kolnp-2004-form 13.1.pdf

1936-KOLNP-2004-FORM 13.pdf

1936-kolnp-2004-form 18.1.pdf

1936-kolnp-2004-form 18.pdf

1936-KOLNP-2004-FORM 2.pdf

1936-kolnp-2004-form 3.1.pdf

1936-kolnp-2004-form 3.pdf

1936-kolnp-2004-form 5.1.pdf

1936-kolnp-2004-form 5.pdf

1936-KOLNP-2004-FORM-27.pdf

1936-kolnp-2004-gpa.pdf

1936-kolnp-2004-gpa1.1.pdf

1936-kolnp-2004-granted-abstract.pdf

1936-kolnp-2004-granted-claims.pdf

1936-kolnp-2004-granted-description (complete).pdf

1936-kolnp-2004-granted-drawings.pdf

1936-kolnp-2004-granted-form 1.pdf

1936-kolnp-2004-granted-form 2.pdf

1936-kolnp-2004-granted-specification.pdf

1936-kolnp-2004-international publication.pdf

1936-kolnp-2004-international search report.pdf

1936-KOLNP-2004-OTHERS-1.1.pdf

1936-kolnp-2004-others.pdf

1936-kolnp-2004-pct priority document notification.pdf

1936-kolnp-2004-pct request form.pdf

1936-KOLNP-2004-PETETION UNDER RULE 137.pdf

1936-KOLNP-2004-REPLY TO EXAMINATION REPORT.pdf

1936-kolnp-2004-reply to examination report1.1.pdf

1936-kolnp-2004-specification.pdf


Patent Number 246709
Indian Patent Application Number 1936/KOLNP/2004
PG Journal Number 11/2011
Publication Date 18-Mar-2011
Grant Date 11-Mar-2011
Date of Filing 16-Dec-2004
Name of Patentee DOLBY LABORATORIES LICENSING CORPORATION
Applicant Address 100 POTRERO AVENUE, SAN FRANCISCO, CA
Inventors:
# Inventor's Name Inventor's Address
1 GUNDRY KENNETH JAMES 100 POTRERO AVENUE, SAN FRANCISCO, CA 94103-4813
2 VENEZIA STEVEN JOSEPH 100 POTRERO AVENUE, SAN FRANCISCO, CA 94103-4813
3 RIEDMILLER JEFFREY CHARLES 100 POTRERO AVENUE, SAN FRANCISCO, CA 94103-4813
4 VINTON MARK STUART 100 POTRERO AVENUE, SAN FRANCISCO, CA 94103-4813
5 ROBINSON CHARLES QUITO 100 POTRERO AVENUE, SAN FRANCISCO, CA 94103-4813
PCT International Classification Number G10L 11/00
PCT International Application Number PCT/US2003/025627
PCT International Filing date 2003-08-15
PCT Conventions:
# PCT Application Number Date of Convention Priority Country
1 10/233,073 2002-08-30 U.S.A.