JPS61246799A - Voice response switch - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

DETAILED DESCRIPTION OF THE INVENTION [Technical Field] The present invention relates to a voice response switch, and more particularly to a voice response switch that operates by recognizing human voice.

[Background Art] As shown in FIG. 6, a conventional upstream voice response switch includes a filter circuit 11 that passes an input signal in a frequency band corresponding to voice, and a level detection circuit 12 that detects the output level of the filter circuit 11. The level detection circuit 1 compares the output of the level detection circuit 12 with a preset reference value.
It is composed of a control circuit 13 that outputs a control signal when the output of 2 is above a reference value, and a switch element 14 that is opened and closed by the control signal, and the input level to the control circuit 13 is above the reference value. A device is provided that sometimes determines that the input signal to the filter circuit 11 is an audio signal.

In this circuit configuration, it is determined whether or not it is a voice only by determining the level of a specific frequency band. Therefore, if the signal has a frequency component in a band that can pass through the filter circuit 11 and has a level higher than the reference value. If the input signal is , the switch element 14 will be activated even if it is a noise other than voice, resulting in a problem of malfunction. Also, even if audio is input, it will be switched to switch element 1.
Since the switch element 14 is actuated regardless of whether the sound is emitted for the purpose of actuating the switch element 4, there is an inconvenience that the switch element 14 may be actuated when the switch element 14 is not desired to be actuated. .

For this reason, as shown in FIG. 7, a voice recognition device 15 is used to compare the control voice stored in advance in the storage unit 16 with the input signal, and when the two match, the switch element 3 is opened or closed. However, when targeting unspecified speakers, there is a problem that a long time is required for arithmetic processing for voice recognition, making it difficult to control the switch element 14 in real time. Moreover, with the current level of technology, there is a problem that the recognition rate is generally low and malfunctions are likely to occur. Furthermore, since increasing the recognition rate requires a large amount of information and calculation, there is a drawback that the processing time is further delayed. On the other hand, when targeting a specific speaker, it is necessary to register the user's own voice before use, and the work required to use it is troublesome.

[Objective of the Invention 1 The present invention has been made in view of the above-mentioned points, and its main purpose is to eliminate multiple formants, which are dominant frequency components characterizing vowels in speech. By extracting and controlling the switch elements by moving vectors in a vector space (or plane) with each formant as a sleeve, it can operate in real time and has a high recognition rate.
Moreover, the purpose is to provide a voice response switch that can be used for unspecified speakers.
It is an object of the present invention to provide a voice response switch that does not misidentify ON control and OFF control of a switch element.

[Disclosure of the Invention] FIG. 5 shows an example of a vowel spectrum,
The dominant frequency component that characterizes a vowel, that is, the frequency component at the peak of the spectrum, is called a formant. In general, a vowel has a plurality of formants, and they are called the 17th orman) F, $2 formant F2, 37th orman) Fs, etc. in descending order of frequency. Among these formants, the contribution rate of the 17th orman) F+ and the 27th orman) F2 is the highest, and if the 17th orman) F+ and the 27th orman) F2 are used, the vowel can be determined with a fairly high degree of accuracy. It is.

Here, if the Japanese vowels /a//i//u//e/10/ are shown on the FIF2 vector plane with the first formant Fl on the horizontal axis and the second formant F2 on the vertical axis, each vowel is represented by the range shown by the broken line in FIG. Formants vary considerably depending on the vocal tract length of each individual, and are expressed with a certain degree of spread on the F and -F2 planes, and the ranges representing each vowel overlap to a large extent. However, in general, the formants of five vowels uttered by the same person in the same environment are F, -F2.
It is approximately pentagonal on a plane, and it is known that even if the environment changes or the speaker changes, the relative positional relationship of the five vowels, that is, the pentagonal shape, will shift in parallel to the retained insect. . Therefore, the relative position when a vowel changes, that is, the change vector, remains approximately constant even if the environment or speaker changes. In other words, if the vector component of vowel /a/ is (800Hz, 1800H2) and the vector space of vowel 10/ is (500Hz, 1000Hz), /a
The component of the change vector from / to 10/ is (-300Hz
, -800Hz), and the components of the change vector remain approximately constant even if the environment or speaker differs. Therefore, in the present invention, a plurality of vowels are made up in succession to form a control voice, and it is determined whether the input signal matches a preset control voice by monitoring the change vector between each vowel. , discloses a voice responsive switch that opens and closes a switch element when an input signal matches a control voice. In addition, in the following explanation, the 17th Orman) FII
I%27 Le Mans) F2 and! However, in order to further increase the recognition rate, the 37th sumant F may be used as the third component of the vector, and generally each If the vowels are represented, the overlapping parts between vowels are removed, which further improves the detection accuracy.

(Example) As shown in FIG. 1, an audio signal is input to a formant extraction circuit 1, and a first formant F1 and a second formant F2 are extracted. The output of the formant extraction circuit 1 is input to a control voice discrimination circuit 2, and when it is determined that the input signal matches a preset control voice, a control signal is output. The output of the control voice discrimination circuit 2 is input to the switch element 3, and when a control signal is input to the switch element 3, the switch element 3 is opened or closed.

FIG. 2 shows an example of the formant extraction circuit 1.

The formant extraction circuit 1 includes a large number of bandpass filters 11, each having a band of 200 Hz and having different pass frequencies. -lln, and each bandpass filter 11. An analog/digital conversion circuit 12 that converts the output signals of ~tin into digital signals, and each bandpass filter 11. It is comprised of an arithmetic circuit 13 consisting of a microprocessor, etc., which detects the 7 or 1 tot from the output level values of .about.lln.

Bandpass filters 11□~lln each have a frequency of 0~200Hz
, 200-400 Hz, 400-600 Hz.

・・・・・・、2200～2400Hz、・・・・・・
The pass frequency bands are different from each other, and when the full band filters 11, to 11n are combined, all frequencies in the audio band can be passed. The arithmetic circuit 13 is the first
7th Lemant) F + G27th Lemant F2 and outputs a phoneme change signal for determining whether the input speech has changed. Note that although the extraction of the seven pulse mants is performed using hardware depending on the circuit configuration, it may also be performed using a software method such as a linear prediction method.

FIG. 3 shows an example of the control speech discriminating circuit 2. When a phoneme change signal is input, the control speech discriminating circuit 2 generates a vector having the first formant F1 and the 27th formant F,2 as components. The first vector holding circuit 22 stores
, a second vector holding circuit 23 stores the vector stored in the first vector holding circuit 22 when the phoneme change signal is input, and a second vector holding circuit stores the vector stored in the first vector holding circuit 22 . A change vector calculation circuit 24 calculates a change vector by subtracting the vector stored in 23, and change vectors between adjacent phonemes in the control speech to drive the switch yt, 3 are stored in a predetermined order. The storage unit 25 compares the output value of the change vector calculation circuit 24 with the setting value stored in the storage unit 25 and determines that the change vector of the input audio signal is in the same order as the change vectors stored in the storage unit 25. a first comparison/determination circuit 26a that outputs a coincidence signal when the match is true and within a set range; and an on control signal that turns on the switch element 3 in response to the coincidence signal output from the first comparison/judgment circuit 26a. The output value of the change vector calculation circuit 24 is compared with the set value stored in the storage unit 25, and the change vector of the input audio signal is stored in the storage unit 25. a second comparison/judgment circuit 26b that outputs a coincidence signal when the order and route of the change vector are within a set range; and a second comparison/judgment circuit 2.
The off control signal generation circuit 28 outputs an off control signal for turning off the switch element 3 in response to the coincidence signal output from the switch element 6b.

In the storage unit 25, change vectors between adjacent phonemes of the set control speech are stored in a form that allows a certain degree of error. In other words, the permissible error range of the change vector is set in consideration of errors in the change vector due to individual differences and environmental differences. For example, from /a/ to 1
As the range of the change vector to 0/(300±Q, Hz
, 800±a2Hz) is set, and 'l
, '2 are set appropriately to adjust the sensitivity. Therefore, in the control speech discriminating circuit 2, each time a phoneme change signal is input to the control speech discriminating circuit 2, the change vector of the input speech signal is checked to see if it is within the tolerance range of the change vector stored in the storage section 25. If it is determined that the change vector between each sound fIA of the input audio signal is within the set range of the change vector of the control sound stored in the storage unit 25, a match signal is sent from the comparison determination circuit 26. is output. Note that the parts of the control voice discrimination circuit 2 other than the storage section 25 can be constructed using the microprocessor 20.

(Operation) The operation will be explained below. First, when some speech signal is input to the formant extraction circuit 1, the seven-score mant extraction circuit 1 extracts the vector components of each input signal on the F+Fz plane, and generates a phoneme change signal at each point in time when the phoneme changes. do. In the control voice discrimination circuit 2, when the first voice is input, first the vector component of the first voice is stored in the first vector holding circuit 22.
When speech is input and a phoneme change signal is obtained, the vector component of the first speech stored in the first vector holding circuit 22 is input to the second vector holding circuit 23, and
The vector component of the second voice is stored in the tJS1 vector holding circuit 22. At this time, the change vector calculation circuit 24
Then, the components of the change vector are calculated from the amount of change between the vector component stored in the second vector holding circuit 23 and the vector component stored in the first vector holding circuit 22. Here, the setting range stored in the storage unit 25 and the component of the change vector as an output value of the change vector calculation circuit 24 are compared, and it is determined whether the change vector is within the setting range stored in the storage unit 25. be done. Here, the output value of the change vector calculation circuit 24 and the set value of the storage section 25 are compared with the first comparison judgment circuit 26m and the second comparison judgment circuit 26b.
However, if the control sounds for generating the ON control signal are /a, ose/, the first comparison judgment circuit 26a compares the output value of the change vector calculation circuit 24 and /&/ It is determined whether the change vector from /e/ to 10/ matches the output value of the change vector calculation circuit 24 and the change vector from /e/ to 10/ in the second comparison judgment circuit 26b.
is compared with the change vector. Next, when the third voice is input, the vector component of the second voice stored in the first vector holding circuit 22 is input to the second vector holding circuit 23, and the vector component of the third voice is input to the first vector holding circuit 22. The component of the change vector from the second voice stored in the second vector holding circuit 23 to the third voice stored in the first vector holding circuit 22 is calculated by the change vector calculation circuit 24. Ru. This change vector is stored in the storage section 25 in both comparison and determination circuits 26a and 26b.
is compared with the set range of the next change vector stored in
It is determined whether the output value of the change vector calculation circuit 24 is within the set range of the change vector stored in the storage section 25. The same operation as described above is repeated until the input signal stops, and when it is confirmed that the change vector of the input audio signal is within the set range stored in the storage unit 25 and is in the correct direction or the route. , a match signal is output from one of the comparison and determination circuits 26a and 26b. 1st
When a match signal is output from the comparison/judgment circuit 26a, the ON control signal generation circuit 27 outputs an ON control signal.
When the second comparison/judgment circuit 26b outputs a match signal, the OFF control signal generation circuit 28 outputs an OFF control signal. The ON control signal and the OFF control signal are input to the switch element 3 to turn the switch element 3 into the ON state a or the OFF state. Needless to say, when the input signal differs from the setting range set in the storage section 25, the switch element 3 maintains its previous state.

The control voice is composed of two or more consecutive vowels, for example, 890. It is e/. In this case, the storage unit 25 stores /, / to 10/, and change vectors from 10/ to /e/ (300±ff1Hz, 800
±ff2Hz), (120±asHzyl 200-!
-a.

Hz) is stored. Here, aI-a is set as appropriate, and the speech recognition rate is adjusted by the set value. Also, as a control voice /i//e//a/10/
The vowel loop may be composed of a vowel string that goes around the vowel loop at least once, with an arbitrary sound in the vowel loop that circulates in the order of /u//i/ as the starting sound. In this case, since the vowel loop goes around the vowel loop once even in the reverse order of the control voice, it is determined whether the switch element 3 is turned on or off depending on the direction in which the change vector rotates the vowel loop. But that's fine.

In the above embodiment, in order to detect a vowel, a vector in a two-dimensional space is used with the first formant F1 and the second formant F2 as vector components, but the 111th formant above F3 (37th orman) is also used as a vector component. In this way, vowels may be determined using vectors in a multidimensional space of three or more dimensions. Further, in the above embodiment, the formant extraction circuit 1 and the control speech discrimination circuit 2 each use a microprocessor, but the microprocessor of both circuits 1.2 may be shared and integrated into one.

[Effects of the Invention] As described above, the present invention can reduce the amount of (
A formant extraction circuit that extracts a first formant and a second formant, and a formant extraction circuit that extracts a first formant and a second formant, and when the formant changes between vowels of a control speech composed of consecutive vowels are in a predetermined order and the amount of change is within a predetermined range. It is composed of a control voice discrimination circuit that outputs a control signal to the terminal, and a switch element that is opened and closed by the control signal.When the control voice is input in the correct order, the control voice discrimination circuit outputs an ON control signal and turns on the switch element. an on control signal generation circuit for setting the state;
It is equipped with an off control signal generation circuit that outputs an off control signal to turn off the switch element when the control voice is input in the reverse order, so that the dominant frequency that characterizes the vowel in the voice is detected. Extract the component 7T Lumant and operate the switch element by moving the audio vector in a vector space formed by a plurality of 7T Lumant.b
・As a result, it was found that speech can be recognized by detecting changes in vowel formants, and although it is aimed at unspecified speakers, the amount of calculation is small and speech recognition is possible. It has the advantage of being reliable. In addition, there is an on-control signal generation circuit that outputs an on-control signal to turn the switch element on when the control audio is input in the normal order, and an on-control signal generation circuit that outputs an off control signal and turns the switch element on when the control audio is input in the reverse order. Since it is equipped with an off control signal generation circuit that turns off the control voice, the change vector of the control voice is similar to the change vector from /e/ to /a/ and the change vector from /u/ to 10/. This has the advantage that the change vectors between the on-control voice and the off-control voice can be completely distinguished, and as a result, no malfunction occurs between the on-control and the off-control.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing an embodiment of the present invention, FIG. 2 is a block diagram showing a formant extraction circuit used in the above, FIG. 3 is a block diagram showing a control speech discrimination circuit used in the same, and FIG. The figure is an operation explanatory diagram showing an example of F, -F 2 diagrams, Fig. 5 is an operation explanatory diagram showing an example of vowel frequency characteristics, Fig. 6 is a block diagram showing a conventional example, and Fig. 7 is another conventional example. FIG. 2 is a block diagram illustrating an example. 1 is a formant extraction circuit, 2 is a control speech discrimination circuit, 3
27 is a switch element, 27 is an on control signal generation circuit, and 28 is an OFF control signal generation circuit. Gu2

Claims (1)

[Claims] (1) A formant extraction circuit that extracts at least a first formant and a second formant from an input speech signal; It is composed of a control voice discrimination circuit that outputs a control signal when the amount of change is within a predetermined range, and a switch element that is opened and closed by the control signal.The control voice discrimination circuit turns on control when control voices are input in the normal order. Equipped with an on control signal generation section that outputs a signal to turn the switch element on, and an off control signal generation circuit that outputs an off control signal and turns the switch element off when control audio is input in reverse order. A voice response switch characterized by comprising: