JPH0634182B2 - Voice recognizer - Google Patents

Description

TECHNICAL FIELD The present invention relates to a voice recognition device for recognizing voice.

2. Description of the Related Art Conventionally, as a voice recognition device that copes with a change in the vocalization speed of a voice, there has been proposed a voice recognition device that performs a DP matching process as disclosed in Japanese Patent Laid-Open No. 50-96104.

First, a voice recognition device that performs voice recognition by this DP matching processing will be described.

In FIG. 1, (1) shows a microphone as an audio signal input section, the audio signal from this microphone (1) is supplied to an acoustic analysis section (2), and the acoustic parameter is measured by this acoustic analysis section (2). A time series Pi (n) is obtained. This acoustic analysis unit (2)
In, for example, the rectified and smoothed output of the bandpass filter bank is the acoustic parameter time series Pi (n) (i = 1, ...,
I; I is the number of channels in the bandpass filter bank, n
= 1, ..., N; N is the number of frames cut out by the voice section determination. ) Is obtained as.

The acoustic parameter time series Pi (n) of the acoustic analysis unit (2) is stored in the standard pattern memory (4) for each recognition target word in the registration mode by the mode changeover switch (3), and DP matching is performed in the recognition mode. It is supplied to one end of the distance calculator (5). In this recognition mode, the standard pattern stored in the standard pattern memory (4) is supplied to the other end of the DP matching distance calculation unit (5).

In this DP matching distance calculation unit (5), a DP matching distance calculation process is performed between the input pattern consisting of the acoustic parameter time series Pi (n) of the voice being input at that time and the standard pattern of the standard pattern memory (4), A distance signal indicating the DP matching distance of the DP matching distance calculating unit (5) is supplied to the minimum distance determining unit (6), and the minimum distance determining unit (6) determines that the DP matching distance is the minimum for the input pattern. The standard pattern is determined, and the recognition result indicating the input voice is obtained at the output terminal (7) from the determination result.

By the way, generally, the number N of frames of the standard pattern stored in the standard pattern memory (4) differs depending on the variation in the utterance speed and the difference in the word length. By the DP matching process, the time axis normalization for coping with the variation in the utterance speed and the difference in the word length is performed.

The DP matching process will be described below. Here, for simplification, the dimension corresponding to the frequency axis direction i of the acoustic parameter time series Pi (n) is omitted, and the parameter time series of the standard pattern is b ₁ , ..., B _N , the parameter time series of the input pattern. the _a 1, ......, as _{a M,} of the endpoints fixed DP
-Pass The DP matching process in the case of will be described.

FIG. 2 shows a conceptual diagram of the DP matching process, in which the horizontal axis shows the input parameters (M = 19) and the vertical axis shows the standard parameters (N-12).
N) There are M × N points on the grid plane, and one distance corresponds to each point. For example, the distance between a ₃ and b ₅ is located at the intersection of a straight line extending vertically from a ₃ and a straight line extending horizontally from b ₅ . In this case, if the Chebyshev distance is taken as the distance, the Chebyshev distance d (3,5) between a ₃ and b ₅ is Becomes (In this case, since the dimension corresponding to the frequency axis direction i is omitted, I = 1.). Then, as a DP-path with a fixed end point, the left grid point (m-1, n) is set to the grid point (m, n) before the grid point (m, n) is connected to this grid point (m, n). Lattice points (m-1, n-
1) and three lower grid points (m, n-1) If only allowed, the starting point, that is, the Chebyshev distance d (1,1) between a ₁ and b ₁ is shown Starting from, 3 directions as a path And the end point, that is, the Chebyshev distance d between a _M and b _N
Indicates (M, N) In the path leading up to, the sum of the distances of the passing grid points is found to be the minimum, and the sum of the distances is used as the number of input parameters M
And the standard parameter number N are subtracted by 1 (M +
The result obtained by dividing by N-1) is the DP matching distance between the parameter pattern time series a ₁ , ..., A _{M of the} input pattern and the parameter time series b ₁ , ..., b _N of the standard pattern. It The initial condition and the recurrence formula showing such processing are the initial condition g (1,1) = d (1,1) recurrence formula And DP matching distance DM (A, B)
Is DM (A, B) = g (M, N) / (M + N-1) and (M + N-1) divides g (M, N) by the difference in the number N of standard pattern frames. This is to correct the difference in the distance value due to. ). By such processing, when the number of standard patterns is L, DP for the input pattern
L matching distances are obtained, and the standard pattern having the smallest distance among the L DP matching distances is used as the recognition result.

According to the voice recognition device based on the DP matching process as described above, it is possible to deal with the fluctuation of the utterance speed and the difference in the word length, that is, the voice recognition with the time axis normalization can be performed.

However, in the case of performing voice recognition by such DP matching processing, the stationary part of the voice is largely reflected in the DP matching distance, and it is easy to erroneously recognize between partially similar words. It became clear.

That is, it can be considered that the acoustic parameter time series pi (n) draws a locus in the parameter space. Actually, since the parameter of each frame n corresponds to one point in the parameter space, one trajectory from the start point to the end point is conceivable when connecting with a curve in the time series direction though it is a sequence of points. For example, when two types of words "SAN" and "HAI" are registered, the respective standard patterns A'and B'are "S", "A", "N", "H", as shown in FIG. A trajectory passing through each phoneme region of "A" and "I" is drawn. When uttering "SAN" in the recognition mode, there are very few similar parts of the standard pattern B'to the input pattern A as a whole, but the "A" part of the "SAN" of this input pattern A is very small. May be more similar to the "A" part of the "SAN" of the standard pattern A'and the "A" part of the "HAI" of the standard pattern B ', and that part (quasi-stationary part) may have more points.

Here, as shown in FIG. 3, the parameters of the input pattern A are generally similar to the parameters of the standard pattern A ′,
A case in which the DP matching process causes an erroneous recognition when it is partially similar to the parameter of the standard pattern B ′ will be described by taking a one-dimensional parameter as an example. In this case, the situation shown in FIG. 3, that is, the input pattern A as shown in FIG. 4 as a one-dimensional parameter time series similar to the relationship between partially similar words; 2, 4, 6, 8, 8,8,8,6,4,4,4,6,8 and standard pattern A'as shown in FIG. 5; 3,5,7,9,9,9,9,7,5,5, 7,9
And a standard pattern B ′ as shown in FIG. 6; 7,6,6,8,8,8,
Consider 8,6,4,4,4. As is apparent from the patterns shown in FIGS. 4 to 6, the input pattern A is a pattern which should be judged as the standard pattern A '. However, the DP of the standard patterns A ′ and B ′ with respect to the input pattern A
Calculation of the matching distance shows that the input pattern A is close to the standard pattern B '.

That is, the DP of the standard pattern A ′ with respect to the input pattern A
As the matching process, as in FIG. 2, the parameter time series of the input pattern A is plotted along the horizontal axis as shown in FIG. 7, 2, 4, 6, 8, 8,
8,8,6,4,4,4,4,6,8 are arranged, and the vertical axis is the parameter time series of the standard pattern A ′; 3,5,7,9,9,9,9,7,5,5, 7 and 9 are arranged, and the Chebyshev distances of the individual parameters of the standard pattern A ′ with respect to the individual parameters of the input pattern A are obtained corresponding to the intersections on the grid plane. Then, the first parameter 2 of the parameter time series of the input parameter A
And the Chebyshev distance d (1,1) = 1 from the first parameter 3 in the parameter time series of the standard parameter A ′.
Of the Chebyshev distance d (13,12) = 1 between the 13th parameter 8 of the parameter time series of the input pattern A and the 12th parameter 9 of the parameter time series of the standard pattern A ′. The point is set as the end point, and as in the case of FIG. 2, the DP-path is allowed to take the left side point, the lower side point and the diagonal left lower side point of the arbitrary point as the previous state with respect to the arbitrary point. In this case (this path is indicated by a solid arrow), the points on the path are d (1,1) -d (2,2) -d.
(3,3) -d (4,4) -d (5,5) -d (6
6) -d (7,7) -d (8,8) -d (9,9) -d
(10,10) -d (11,10) -d (12,10) -d (13,11)-
There are 14 points of d (13,12), the total sum of the distances is 24, and the DP matching distance DM (A, A ') is 1.

On the other hand, the DP of the standard pattern B'for the input pattern A
The matching process is performed as shown in FIG. 8 as in the case shown in FIG. That is, the individual parameters of the input pattern A; the individual parameters of the standard pattern B'for the 2,4,6,8,8,8,8,6,4,4,4,6,8; 7,6, 6,8,8,8,8,6,4,4,4
Chebyshev distance is calculated, and if it is allowed to take a point on the left side, a point on the lower side, and a point on the lower left side of the diagonal point of the arbitrary point as the previous state for the DP-path (the solid line arrow , And points on the path are d (1,
1) -d (2,2) -d (3,3) -d (4,4) -d
(5,5) -d (6,6) -d (7,7) -d (8,
8) -d (9,9) -d (10,10) -d (11,11) -d
There are 13 points of (12,11) -d (13,11), and the sum of the distances is 15, and this DP matching distance DM (A, B ')
Is 0.65.

This DP-path is in 3 directions As is clear from the result, the input pattern A is the DP
It is determined as a standard pattern B ′ with a small matching distance,
The result to be judged cannot be obtained. As described above, in the DP matching process, misrecognition is likely to occur between words that are partially similar.

Further, in the DP matching processing, the number N of frames of standard patterns is indefinite as described above, and it is necessary to perform DP matching processing for all standard patterns with respect to the input pattern. However, there was a problem in the storage capacity and calculation amount of the standard pattern memory (4).

SUMMARY OF THE INVENTION In view of the above, the present invention has a relatively small number of word recognitions even between words that are partially similar to each other, and has a relatively small storage capacity and calculation amount of a standard pattern memory. The purpose is to obtain a voice recognition device.

SUMMARY OF THE INVENTION The voice recognition device of the present invention is, for example, as shown in FIG. 9, a voice signal input unit (1) and a conversion unit (2) for converting a voice signal from the voice signal input unit (1) into an acoustic parameter sequence. And an estimation unit (21) that estimates a trajectory in the parameter space from the acoustic parameter sequence, and a recognition unit (4) that recognizes the voice signal based on the trajectory estimated by the estimation unit (21), ( 25), and (6), and according to the speech recognition apparatus of the present invention, there is relatively little erroneous recognition even between words that are partially similar, In addition, there is an advantage that a standard pattern memory having a relatively small storage capacity and calculation amount can be obtained.

Embodiment An embodiment of the speech recognition apparatus of the present invention will be described below with reference to FIGS. 9 to 17. This FIG. 9 thru | or
In FIG. 17, parts corresponding to those in FIGS. 1 to 8 are designated by the same reference numerals, and detailed description thereof will be omitted.

In FIG. 9, (1) indicates a microphone as an audio signal input section, and the audio signal from this microphone (1) is supplied to the amplifier (8) of the acoustic analysis section (2), and the amplifier (8) Low-pass filter with a cutoff frequency of 5.5 KHz for audio signals
12-bit A / with sampling frequency of 12.5 KHz via (9)
It is supplied to the D converter (10) and the digital audio signal of this A / D converter (10) is supplied to the 15-channel digital bandpass filter bank (11 _A ), (11 _B ), ..., (11 _O ). Supply.

This 15-channel digital bandpass filter bank (11 _A ), (11 _B ), ..., (11 _O ) is composed of, for example, a Butterworth fourth-order digital filter, and 250 Hz to 5.5 KH
Bands up to z are allocated so that they are evenly spaced on the logarithmic axis. Then, each digital bandpass filter (11
_{A), (11 B),} ......, (11 O) of the output signal 15 channels of the rectifier _{(12 A), (12 B} ), ......, (12 O) To each supply, these rectifiers (12 _A ), (12 _B ),…, (12 _O ).
The squared output of is supplied to the 15-channel digital low-pass filters (13 _A ), (13 _B ), ..., (13 _O ), respectively. These digital low-pass filters (13 _A ), (13 _B ), ...
, (13 _O ) are composed of FIR (finite impulse response type) low-pass filter with a cutoff frequency of 52.8 Hz.

Then, each digital low-pass filter (13 _A ), (1
3 _B ), ……, (13 _O ) output signal with sampling period 5.1
Supply to the 2ms sampler (14).

The sampler (14) samples the output signals of the digital low-pass filters (13 _A ), (13 _B ), ..., (13 _O ) every 5.12 ms frame period,
The sampling signal of is supplied to the sound source information normalizer (15). The sound source information normalizer (15) removes a difference in vocal cord sound source characteristics depending on the speaker of the voice to be recognized.

That is, for each sampling signal Ai (n) (i = 1, ..., 15; n: frame number) supplied from the sampler (14) every frame period, A′i (n) = log (Ai (n ) + B) ... (1) Logarithmic transformation is performed. In this equation (1), B is set to a value such that the noise level is hidden by the bias. Then, the vocal cord sound source characteristic is approximated by an expression yi = a · i + b. The counts of a and b are determined by the following equation.

When the normalized parameter of the sound source is Pi (n), the parameter Pi (n) is Pi (n) = A′i (n) − {a (n) · i + b when a (n) <0. (n)} is expressed as (4).

When a (n) ≧ 0, only level normalization is performed, and the parameter Pi (n) is Is represented.

Normalized parameters of sound source characteristics by such processing
The pi (n) is supplied to the parameter memory (16) in the voice section.
The in-voice-section parameter memory (16) receives a voice section determination signal from a voice section determining unit (17), which will be described later, and stores a normalized sound source characteristic parameter Pi (n) for each voice section.

On the other hand, the digital voice signal of the A / D converter (10) is converted into the zero cross counter (18) of the voice section determination unit (17) and the power calculator.
Supply to (19) respectively. This zero cross counter (18) is 5.
Every 12 ms, the number of zero crossings of 64 points of digital audio signals in that section is counted, and the count value is counted by the audio section determiner (2
0) to the first input terminal. Also, the power calculator (19)
The power of the digital voice signal in the section, that is, the sum of squares is calculated every 5.12 ms, and the power signal indicating the power in the section is supplied to the second input terminal of the voice section determiner (20). Further, the sound source normalization information a (n) and b (n) of the sound source information normalizer (15) are supplied to the third input terminal of the voice section determiner (20). Then, in the voice section determiner (20), the zero cross number, the intra-section power, and the sound source normalization information a (n) and b (n) are processed in a composite manner to perform a process of determining silence, unvoiced sound and voiced sound, Determine the voice section. The voice section determination signal indicating the voice section of the voice section determiner (20) is supplied to the intra-voice section parameter memory (16) as the output of the voice section determination unit (17).

Acoustic parameters Pi (n) with the sound source characteristics normalized for each voice section stored in this voice section parameter memory (16)
Is supplied to the NAT processing unit (21) in the time-series direction (this NAT is the head of the Normalization Along Trajectory). This NAT processing unit (21) is a NAT
As a process, a trajectory in the parameter space is estimated from the acoustic parameter time series Pi (n), and a new acoustic parameter time series Qi (m) is formed based on this trajectory.

Here, the NAT processing unit (21) will be further described.
Acoustic parameter time series Pi (n) (i = 1, ..., I; n =
1, ..., N) draws a sequence of points in the parameter space. First
Figure 10 shows an example of a sequence of points distributed in a two-dimensional parameter space. As shown in FIG. 10, the point sequence of the non-stationary part of the voice is roughly distributed, and the quasi-stationary part is densely distributed. This is clear from the fact that the parameters do not change if they are completely stationary, and in that case the point sequence stays in the parameter space.

FIG. 11 shows an example in which a locus is drawn by a smooth curve on the point sequence as shown in FIG. If the locus can be estimated with respect to the point sequence as shown in FIG. 11, it can be considered that the locus is almost unchanged with respect to the fluctuation of the voice utterance speed. because,
Most of the difference in the time length due to the variation in the vocalization rate of the speech is due to the temporal expansion / contraction of the quasi-stationary portion (corresponding to the difference in the point sequence density of the quasi-stationary portion in the point sequence shown in FIG. 10). This is because the influence of the time length of the stationary part is considered to be small.

In the NAT processing section (21), attention is paid to such invariance of the locus with respect to the variation of the vocalization speed of the voice, and the time axis normalization is performed.

That is, first, with respect to the acoustic parameter time series Pi (n), the starting point P
Estimate the locus drawn by a continuous curve from i (1) to the end Pi (N), and draw the curve showing this locus. (0 ≦ s ≦ S). In this case, Basically does not have to be May be such that it approximately passes through the entire point sequence.

Second estimated The length SL of the locus is obtained from, and a new point sequence is resampled at a constant length along the locus, as indicated by the circles in FIG.
For example, when sampling at M points, the locus is resampled on the basis of a fixed length, that is, the resampling interval T = SL / (M-1). If this sequence of phosphorus-supplemented points is Qi (m) (i = 1, ..., I; m = 1, ..., M), Is.

The new parameter time series Qi (m) thus obtained has the basic information of the locus, and is a parameter which is almost invariable with respect to the fluctuation of the speech production speed. That is, the new parameter time series Qi (m) is a parameter time series that has been time-axis normalized.

For this kind of processing, the parameter memory in the voice section (16)
The acoustic parameter time series Pi (n) is supplied to the trajectory length calculator (22). This trajectory length calculator (22)
Pi (n) is to calculate the length of the trajectory by the linear approximation drawn in the parameter space, that is, the trajectory length. In this case, the Euclidean distance D (a _i , b _i ) between the one-dimensional vectors a _i and b _i is Is. Therefore, one-dimensional acoustic parameter time series Pi (n)
From (i = 1, ..., I; n = 1, ..., N), the distance S (n) between adjacent parameters in the time series direction when the trajectory is estimated by linear approximation is S (n) = D (Pi (n + 1), Pi (n)) (n = 1, ..., N-1)
…… (7) is represented. The distance SL (n) from the first parameter Pi (1) to the nth parameter Pi (n) in the time series direction is Is represented. Note that SL (1) = 0. Furthermore, track length SL
Is Is represented. The trajectory length calculator (22) is configured to perform the signal processing shown in the equations (7), (8) and (9).

The trajectory length signal indicating the trajectory length SL of the trajectory length calculator (22) is supplied to the interpolation interval calculator (23). This interpolation interval calculator (23)
Is for calculating a constant length phosphorus sampling interval T for re-sampling a new point sequence by linear interpolation along the locus. In this case, if resampling is performed at the point M, the resampling interval T is expressed as T = SL / (M-1) (10). The interpolation interval calculator (23) is configured to perform the signal processing shown by the equation (10).

The resampling interval signal indicating the resampling interval T of the interpolation interval calculator (23) is supplied to one end of the interpolation point extractor (24), and the acoustic parameter time series Pi (n) of the parameter memory (16) in the voice section is supplied. Is supplied to the other end of the interpolation point extractor (24). This interpolation point extractor (24) is an acoustic parameter time series Pi
(n) A locus in the parameter space, for example, a resampling interval T along a locus obtained by linear approximation between parameters.
In, a new sequence of points is resampled, and a new acoustic parameter time series Qi (m) is formed from this new sequence of points.

Here, the signal processing in this interpolation point extractor (24)
A description will be given along the flow chart shown in the figure. First, the block (24
In a), the value 1 is set to the variable J indicating the number of the resampling points in the time series direction, and the value 1 is set to the variable IC indicating the number of the acoustic parameter time series Pi (n) in the time series direction.
Is set. Then, the variable J is incremented in the block (24b), and the number in the time series direction of the resampling point at that time is determined depending on whether or not the variable J at that time is (M-1) or less in the block (24c). Determines if it is not the last number that needs to be resampled, and if not, the first at block (24d)
The resampling distance DL from the th-th resampling point to the J-th resampling point is calculated, and the block (24e)
The variable IC is incremented at, and the resample distance DL is at the first of the acoustic parameter time series Pi (n) at block (24f).
The 1st parameter Pi (1) to the ICth parameter Pi (I
Depending on whether it is smaller than the distance SL (IC) to C), it is judged whether the resampling point at that time is located on the locus starting point side from the parameter Pi (IC) at that time on the locus, and the position If not, in block (24e) variable I
After incrementing C, the position of the resampling point and the parameter Pi (IC) on the locus is compared again in block (24f), and the resampling point is located on the locus on the starting point side of the parameter Pi (IC). When it is determined that
A new acoustic parameter Qi (J) along the locus is formed by resampling in the block (24g). That is, first, from the re-sampling distance DL by the J-th resampling point, the distance by the (IC-1) -th parameter Pi (IC-1) located closer to the starting point than the J-th resampling point.
SL (IC-1) is subtracted and the (IC-1) th parameter Pi
Find the distance SS from (IC-1) to the Jth resampling point. Next, the distance S (n) between the parameter Pi (IC-1) and the parameter Pi (IC) located on both sides of this J-th resampling point on the locus (this distance S (n) is (7) This distance SS is divided SS / S (IC-1) by the signal processing shown in the equation), and the result SS / S (IC-1) of this division is the J-th relocation on the locus. Difference between parameters Pi (IC) and Pi (IC-1) located on both sides of the sampling point Pi (IC) −Pi (IC−
1)) is multiplied (Pi (IC) -Pi (IC-1)) * SS / S (IC-1),
On the locus, the J-th resampling point is located adjacent to the start point side of this resampling point (IC-1)
The interpolation amount from the th parameter Pi (IC-1) is calculated, and this interpolation amount and the (IC-1) th parameter Pi (IC) located adjacent to the start point side from the Jth resampling point -1)
And a new acoustic parameter Qi (J) along the trajectory is added.
Is formed. Fig. 14 shows the trajectory of the two-dimensional acoustic parameter time series P (1), P (2), ..., P (8) by linear approximation between the parameters and linear interpolation along this trajectory. 6 new acoustic parameter time series Q (1), Q (2),
..., the example which formed Q (6) is shown. In addition, this block (24
In g), one dimension (i = 1, ...
, I) signal processing is performed.

In this way, the start and end points (these are these in blocks (24b) to (24g)) Is. A new acoustic parameter time series Qi (m) is formed by resampling of (M-2) points excluding).

New acoustic parameter time series Qi of this NAT processing unit (21)
(m) is stored in the standard pattern memory (4) for each recognition target word in the registration mode by the mode selection switch (3),
In the recognition mode, it is supplied to one end of the Chebyshev distance calculation unit (25). In this recognition mode, the standard pattern stored in the standard pattern memory (4) is supplied to the other end of the Chebyshev distance calculation unit (25). In this Chebyshev distance calculation unit (25), a new time series of normalized acoustic parameters of the time axis of the voice being input at that time
Input pattern consisting of Qi (m) and standard pattern memory (4)
Chebyshev distance calculation processing with the standard pattern of is performed.

Then, the distance signal indicating the Chebyshev distance is supplied to the minimum distance determination unit (6), and the minimum distance determination unit (6) determines the standard pattern that minimizes the Chebyshev distance with respect to the input pattern. The recognition result indicating the input voice is supplied to the output terminal (7).

The operation of the speech recognition apparatus thus configured will be described.

The sound signal from the microphone (1) is normalized by the sound analysis unit (2) for each sound section, and the sound source characteristics are normalized in time series Pi parameter.
(n) and this acoustic parameter time series Pi (n) is NA
It is supplied to the T processing unit (21), and the NAT processing unit (21) estimates a trajectory by linear approximation in the parameter space from the acoustic parameter time series Pi (n), and based on this trajectory, the time axis normalization is performed. New acoustic parameter time series made
Qi (m) is formed, and in the registration mode, this new acoustic parameter time series Qi (m) is stored in the standard pattern memory (4) via the mode changeover switch (3).

In the recognition mode, the new acoustic parameter time series Qi (m) of the NAT processing unit (21) is supplied to the Chebyshev distance calculation unit (25) via the mode changeover switch (3) and the standard pattern memory ( The standard pattern of 4) is supplied to the Chebyshev distance calculation unit (25). No. 4 in Figures 15 to 17
Parameter time series of one-dimensional input pattern A shown in Figs. 6 to 6; 2,4,6,8,8,8,8,6,4,4,4,6,8, parameters of standard pattern A ' Time series: 3,5,7,9,9,9,9,7,5,5,7,9,
Parameter time series of standard pattern B ': 7,6,6,8,8,8,8,
The parameter time series of the one-dimensional input pattern A, which is obtained by estimating the locus by linear approximation of 6,4,4,4 in the NAT processing unit (21) and setting the resampling point to 8 points; , 6,8,6,4,6,
8, standard pattern A'parameter time series; 3,5,7,9,7,
5,7,9, parameter time series of standard pattern B '; 7,6,7,
Shows 8,7,6,5,4 respectively. In this case, the trajectory in the parameter space is estimated from the acoustic parameter time series Pi (n), and a new acoustic parameter time series Qi is generated along this trajectory.
Since (m) is formed, time axis normalization is performed by the acoustic parameter time series Pi (n) itself obtained by converting the input voice.
Then, in the Chebyshev distance calculation unit (25), the Chebyshev distance 8 between the input pattern A and the standard pattern A ′ is set.
And the input pattern A and the standard pattern B ′ are calculated.
Chebyshev distance 16 between and is calculated, and these distances 8
And distance signals indicating the distance 16 are supplied to the minimum distance determination unit (6), and the minimum distance determination unit (6) determines that the distance 8 is the distance 16
It is determined that the standard pattern A is the input pattern A'because it is smaller than the above, and the recognition result indicating that the input voice is the standard pattern A is output from the determination result from the output terminal (7).
Can be obtained. Therefore, it is possible to perform voice recognition with relatively few erroneous recognitions even between words that are partially similar.

As described above, according to the voice recognition device of the present invention, the microphone (1) as the voice signal input unit is provided, and the voice signal from the voice signal input unit (1) is used as the acoustic parameter time series Pi (n).
, And a trajectory based on the linear approximation in the parameter space is estimated from the acoustic parameter time series Pi (n), and the voice signal is recognized based on this trajectory, so that it seems to be partially similar. There is an advantage that it is possible to recognize speech with relatively few erroneous recognition even between words.
Further, there is an advantage that the amount of calculation for processing can be relatively reduced.

Here, the speech recognition apparatus of the present invention for performing NAT processing and DP
The difference in the amount of calculation from the conventional speech recognition apparatus that performs matching processing will be described.

The average calculation amount in the DP matching distance calculation unit (5) per standard pattern for the input pattern is α,
When the average calculation amount in the Chebyshev distance calculation unit (25) is β and the average calculation amount in the NAT processing unit (21) is γ,
The calculation amount C _{1 in the} DP matching process for J standard patterns is C ₁ = α · J (11). The computation amount C ₂ when NAT processing is performed on J standard patterns is C ₂ = β · J + γ (12). In general, the average calculation amount α has a relationship of α >> β with respect to the average calculation amount β. Therefore, The relationship is established, i.e. the amount of computation C ₁ according to the recognition target vocabulary number is increased becomes C ₁ »C ₂ made relationship with calculation amount C _2, according to the present invention a speech recognition apparatus for performing NAT processing, There is a benefit that the amount of calculation can be greatly reduced.

Further, since the new acoustic parameter time series Qi (m) obtained from the NAT processing unit (21) can be set to a constant number of parameters in the time series direction, the storage area of the standard pattern memory (4) can be effectively used, There is an advantage that the storage capacity can be made relatively small.

In the above embodiment, the acoustic parameter time series Pi (n)
The trajectory in the parameter space is estimated from the
Although the case has been described where Qi (m) is formed by linear interpolation, the trajectory is estimated by arc approximation, spline approximation, etc. It can be easily understood that the same effects as those of the above-described embodiment can be obtained even if they are formed by the above method. Further, in the above-mentioned embodiment, the trajectory in the parameter space is estimated from the acoustic parameter time series Pi (n), and a case is described in which a new acoustic parameter time series Qi (m) is formed based on this trajectory. However, by estimating the trajectory in the parameter space from the acoustic parameter frequency sequence and forming a new acoustic parameter frequency sequence based on this trajectory, the frequency characteristic of the audio signal can be normalized. Furthermore, in the above-mentioned embodiment, the trajectory in the parameter space is estimated from the voice parameter time series Pi (n), and a new acoustic parameter time series Qi (m) is formed by resampling along this trajectory. As I said, I extracted the coefficient that shows the shape of the trajectory,
It is possible to perform voice recognition by using this coefficient as a new time series of acoustic parameters. Further, the present invention is not limited to the above-mentioned embodiments, and it goes without saying that various other configurations can be adopted without departing from the gist of the present invention.

EFFECTS OF THE INVENTION According to the speech recognition apparatus of the present invention, a speech signal input unit is provided, a speech signal from this speech signal input unit is converted into an acoustic parameter sequence, and a trajectory in the parameter space is estimated from this acoustic parameter sequence. Since the voice signal is recognized based on this locus, it is relatively unlikely to misrecognize even between words that are partially similar to each other, and the storage capacity and operation of the standard pattern memory are relatively small. There is a benefit of being able to obtain a relatively small quantity.

[Brief description of drawings]

FIG. 1 is a block diagram showing an example of a voice recognition device that performs voice recognition by DP matching processing, and FIG. 2 is a DP.
FIG. 3 is a conceptual diagram for explaining the matching process, FIG. 3 is a diagram for explaining the trajectory in the acoustic parameter space, and FIG.
FIGS. 5, 5 and 6 show one-dimensional input patterns A,
FIG. 7 is a diagram showing examples of the standard pattern A ′ and the standard pattern B ′, and FIG. 7 is provided for explaining the time-axis normalization by the DP matching processing of the parameter time series of the input pattern A and the parameter time series of the standard pattern A ′. FIG. 8 is a diagram for explaining the normalization of the time axis by the DP matching processing of the parameter time series of the input pattern A and the parameter time series of the standard pattern B ′, and FIG. 9 is the speech recognition apparatus of the present invention. FIG. 10, FIG. 11, FIG. 12, FIG. 12 and FIG. 14 are diagrams showing an embodiment of the present invention, respectively.
The figure is a flow chart for explaining the interpolation point extractor.
FIG. 17 and FIG. 17 are diagrams showing the one-dimensional acoustic parameter time series of the input pattern A, the standard pattern A ′ and the standard pattern B ′ processed by the NAT processing section, respectively. (1) is a microphone as an audio signal input section, (2) is an acoustic analysis section, (3) is a mode switch, (4) is a standard pattern memory, (6) is a minimum distance determiner, (11 _A ), (11 _B ) ， …… ， (1
1 _O ) is a 15-channel digital bandpass filter bank, (16) is a parameter memory in the voice section, and (21) is a NAT.
Processing unit, (22) trajectory length calculator, (23) interpolation interval calculator,
(24) is an interpolation point extractor, and (25) is a Chebyshev distance calculation unit.

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Masao Watanabe 6-35 Kita-Shinagawa, Shinagawa-ku, Tokyo Sony Corporation (56) References Proceedings of the Acoustical Society of Japan, October 1984 1-9 -9P. 17-18

Claims (1)

[Claims] 1. An audio signal input unit, a conversion unit for converting an audio signal from the audio signal input unit into an acoustic parameter sequence, an estimation unit for estimating a trajectory in the parameter space from the acoustic parameter sequence, and the estimation. A voice recognition device comprising: a recognition unit that recognizes the voice signal based on the trajectory estimated by the unit.