JPS6258520B2 - - Google Patents

Description

[Detailed Description of the Invention] [Technical Field of the Invention] The present invention has L types of filters whose impulse responses are linear prediction coefficients obtained from L types of standard waveform sequences, arranged in parallel, and which generates Ajichi's signal waveform sequence. In a signal waveform recognition device in which the category to which an input signal waveform series belongs is the filter subscript that minimizes the sum of squares of its output when input, L types of filters are used to prevent misrecognition caused by fluctuations in filter output. For each output, one or more K
A signal waveform recognition method that reduces fluctuations added to the filter output by preparing a series in which each of the series has an orthonormal relationship and removing components in the direction indicated by the series from the filter output. It is related to the method.

[Technical background of the invention]

There are various signal waveform recognition methods, one of which is a method called the residual waveform power method. Since the present invention is an improved version of the residual waveform power method, the residual waveform power method will be explained.

The signal waveform series {Xn} is expressed as the pole of the transfer relationship is {α
_n } ^P Let the impulse response of the filter be given by _n=1 . In other words, if the transfer relationship is G _(z) , then becomes. therefore, becomes.

The filter that whitens the signal waveform series {x _o } is a filter with the opposite characteristics of G _(z). It is. Here, {a _k } ^P _k=1 is a linear prediction coefficient. If the signal waveform series {x _o } is passed through the filter A _(z) , then becomes. Since the actual waveform contains a dominant term, the residual can be expressed as {e _o }. is written.

Since the linear prediction coefficients {a _k } are originally selected so as to minimize the sum of squares of the residuals, the sum of squares of the output of the inverse filter A _(z) is minimized. A method that applies this principle is the residual waveform power method.

It is assumed that there are L categories of signal waveform series. For each linear prediction coefficient {a(l) _k }
Determine ^{P L} _{k=1 l=1} and apply the inverse filter A(l)
Make _(z) . The signal waveform sequence {x(l) _o } is the filter G(l) _(z) = 1/
A
(l) Suppose that it is the output from _(z) . Filter A(l) _(z
) is {e(l) _o }, then becomes. If you use other filters, becomes. Between e(l) _o and e(l) _o ′, Because of this relationship, the subscript of the inverse filter can be set as the category to which the signal waveform series belongs.

[Problems with background technology]

The above method has the advantage that high-speed recognition processing is possible because the linear prediction coefficients are prepared in advance and there is no procedure for calculating the linear prediction coefficients during the recognition processing time.

However, the generation filter G(l) _(z) of the signal waveform series
If the waveform {x(l) _o } changes, the waveform {x(l) o } changes.
If we calculate equations (6) and (7) using the fluctuated waveform as {(l) _o }, we get , but not necessarily I cannot say that it will be. If the inequality sign is reversed, it will be a misrecognition.

[Purpose of the invention]

An object of the present invention is to realize a recognition device that improves the drawbacks of the residual waveform power method and has the advantages at the same time.

[Summary and effects of the invention]

The present invention enables unknown input signal waveform sequences of
A residual waveform sequence is obtained through a filter that uses the linear prediction coefficients of known standard signal waveform sequences of L types of classes as impulse response waveforms, and the output of the sum of squares of this residual waveform sequence is used to determine the class to which the input signal waveform series belongs. In the recognition method for determining the auxiliary waveform sequence, one or more auxiliary waveform sequences are generated which are set in advance for each of the L types and for removing some fluctuations in the input signal waveform sequence, and the auxiliary waveform sequence and the residual waveform sequence are The method is characterized in that an inner product value with the difference waveform series is determined, the sum of squares of each inner product value is subtracted from the output of the sum of squares of the residual waveform series, and the subtraction result is used to determine the class to which the input signal waveform series belongs. That is.

Therefore, in a speech recognition system that is supplied with speech waveforms as an input signal waveform series, it is possible to eliminate the influence of individual differences and perform highly accurate identification, especially for unspecified speakers.

Furthermore, when identifying various input signal waveforms, not limited to voice waveforms, it is possible to perform identification that is resistant to deformations and fluctuations.

[Embodiments of the invention]

Before explaining the specific configuration of the device of the present invention,
An identification method that can be achieved with the device of the present invention will be described.

The vector e ^(l) _i = (e _i1 e _i2 ...e _iN ) ^T created by the residual waveform sequence when the signal waveform sequence generated from category l is passed through its inverse filter A ^(l) _(z) is It is assumed that Fourier expansion can be performed using an orthonormal vector {μ ^(l) _k } ^N _k=1 . Now consider how to choose |μ(l) _k .
The matrix created by vector e ^(l) _i is E ^(l) _i = (e ^(l) _i e ^(l) _i+1 ...e ^(l)
_i+N-1 )(12) Then, the covariance matrix V ^(l) _i becomes V ^(l) _i = E ^(l)T _i E ^(l) _i . Considering the mean of the covariance matrix, Then, the average of the P-order covariances is calculated. Here I is an arbitrary large number.

Eigenvalue problem of V ^(l) V ^(l) 〓 ^(l) _k = λ ^(l) _k 〓 ^(l) _k , ‖‖μ ^(l) _k ‖=1, k=1, 2,..., N (15 ), the eigenvalue λ ^(l) _k represents the dispersion of μ ^(l) _k in the direction. Therefore, we will adopt K items from the one with the largest eigenvalue, and if we set d ^(l) _k = (e ^(l) , 〓 ^(l) _k ), k = 1, 2, ..., K (16), the category Any residual sequence vector of l can be Fourier expanded as 〓(l)=μ(l)〓(l)+O (17). Here, μ ^(l) = (〓 ^(l) ₁ 〓
^(l) ₂ ...〓 ^(l) _k ), 〓 ^(l) = (d ^(l) ₁ d ^(l
) ₂ ...d ^(l) _k ) ^T.

From equation (15), 〓 ^(l) _k can be formally set to N, but if the dimension of the prediction filter is P, a maximum of P 〓 ^(l) _k can be calculated.

{〓 ^(l) _k } ^K Since _k=1 has been selected from the one with the largest variance, if μ ^(l) d ^(l) can be removed from equation (17), the series {e ^(l) _o } can be expected to be small.

〓 From ^(l) , if we take the component in the direction defined by {〓 ^(l) _k } ^K _k=1, then ^(l) has polarity in the direction of {〓 ^(l) _k } ^K _k=1. becomes.

If we calculate, 〓 ^(l) has the above properties, so in this sense, 〓 ^(l) _i is called a polarity error.

〓 Judging by the square of the norm of ^(l) , e ^(l
) can be recognized more resistant to fluctuations than by the square of the norm. Therefore, if we calculate the square of the norm of 〓 ^(l) , the following equation holds true since (〓 _k , 〓 _k ′)=δ _kk ′.

The method of recognizing using equation (19) is called the polarity error identification method. The polarity error identification method is similar to the residual waveform power method in that prediction coefficients are prepared in advance, and inherits its advantages. Furthermore, by preparing one or more K orthonormal vectors {〓 ^(l) _k } in advance and taking the square of the inner product with the residual sequence from the square of the norm of the residual sequence, it is possible to statistically This recognition method has increased tolerance in the direction of large variance, making it resistant to fluctuations.

An example of a specific device will be described below with reference to the drawings. The overall diagram of the process is shown in Figure 1.

The signal waveform series {x _o } is generated by polarity error sum-of-square calculation circuits 11...1l... which are prepared for the number of categories L.
Sent to 1L. The arithmetic circuit 1l calculates Equation 19 and outputs ‖〓 ^(l) ‖ ² as a result. The next minimum value detection circuit 2 detects the minimum l,
Output l as the recognition result.

FIG. 2 is a concrete block diagram of the circuit 1l, which is one of the polarity error sum-of-square calculation circuits shown in FIG.

The signal waveform sequence x _o is the inverse filter A ^(l) _(z) 31
and the inverse filter A ^(l) _(z) 31 outputs the residual waveform sequence e
^(l) _o
Output. The circuit 32 is a circuit that calculates the square of the norm of the residual waveform series (only this circuit is used for the residual waveform power method), and the output is ‖〓 ^(l) ‖ ²
It is. Further, the circuit 33 is a circuit that calculates the component {μ ^(l) _k } ^K _{k = 1} included in the square of the norm of the residual waveform series, and is a newly added part in the present invention. Then, the outputs from the circuits 32 and 33 are subtracted, and the result is ‖〓 ^(l) ‖ ² .

FIG. 3 specifically shows the circuit 33 that calculates the component {〓 ^(l) _k } ^K _k=1 included in the square of the norm of the residual waveform series in FIG. 2. be.

By the circuits 411,..., 41k,..., 41K,
Calculate the component of {〓 ^(l) _k } ^K _k=1 included in e,
The circuits 421, . . . , 42k, . . . 42K calculate the square value. Finally, the circuit 43 calculates the total sum.

For example, as a speech recognition system for identifying vowels, the arithmetic circuits 11,..., 1l,
..., 1L correspond to each vowel.

In addition, the input signal waveform series x _o is A/
A digital signal sequence {x
_o } ⁿ¹ _o=o0 is used.

Furthermore, the auxiliary waveform series 〓 ^(l) _k is determined by collecting sounds produced by a large number of people in advance for each vowel, and using these, using equation (15), etc., and its value is stored in a storage device (not shown). is stored in advance and supplied to the circuit 33.

[Modified example of the invention]

(1) The present invention is not limited to identifying voice waveforms, but can also be used to identify electrocardiogram waveforms, etc. Also,
N-dimensional waveforms other than these one-dimensional waveforms can also be realized by using an n-dimensional filter. For example, when n=2, it is also possible to identify signal waveforms obtained from planar images.

(2) Although all of the above embodiments are constructed using digital circuits, at least a portion thereof may be realized by program control using a microcomputer or the like, or may be constructed using analog arithmetic circuits. In this case, the product-sum circuit,
For the sum-of-squares circuit, an element capable of calculating an inner product, for example, an element using an optical filter, a surface acoustic wave element, etc. can be used.

(3) The number K of variation directions for each class may be different for each class.

[Brief explanation of the drawing]

FIG. 1 is a diagram showing an embodiment of the present invention, and FIGS. 2 and 3 are diagrams showing an example of the configuration of each part of the embodiment of the present invention. 11,..., 1l,..., 1L... Arithmetic circuit, 2...
...Minimum value detection circuit, 31...Inverse filter, 32...
...Sum of squares circuit, 33...Inner product circuit.

Claims (1)

[Claims] 1) A residual waveform sequence is obtained by passing an unknown input signal waveform sequence of class 1 through a filter whose impulse response waveform is the linear prediction coefficient of a known standard signal waveform sequence of L types, and then squares this residual waveform sequence. In a recognition method that determines the class to which an input signal waveform sequence belongs based on the sum output, one or more auxiliary waveform sequences are set in advance for each of the L types and are used to remove a certain amount of variation in the input signal waveform sequence. generated, calculate the inner product value of this auxiliary waveform series and the residual waveform series, subtract the sum of squares of each inner product value from the sum of squares output of the residual waveform series, and use this subtraction result to calculate the input signal waveform. A signal waveform recognition method characterized by determining the class to which a sequence belongs.