JPS59121097A - Voice recognition equipment - 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 of the Invention] The present invention relates to a speech recognition device capable of fully and reliably recognizing input speech uttered in synchronization with a signal tone.

[Technical background of the invention and its problems]

Recently, the development of speech recognition technology has been remarkable, and there are some speech recognition devices that recognize isolated speech with high accuracy, and speech typewriters that input speech that is divided into monosyllables. It has now been put into practical use. by the way,
In the case of the above-mentioned word speech recognition device, it is not sufficient to recognize only one uttered sound, but when recognition of one sound is completed, it is necessary to immediately perform recognition processing for the next one sound. Conventionally, therefore, a signal sound such as "beep" is output every time one sound is recognized, and the next sound is prompted to be uttered in synchronization with this signal sound. In addition, since voice typewriters handle syllables that are continuously uttered, in order to alleviate the problem of segmentation, devices such as outputting the above-mentioned signal tone at a predetermined period to instruct the timing of voice production are taken. has been done. Therefore, the speaker only has to monitor the signal tone and utter the voice in synchronization with it.

Now, in conventional speech recognition devices, the recognition results of input speech are displayed using a display device such as a CRT character display attached to the device. Therefore, in order to confirm the recognition result, the speaker needs to visually check it, and the advantages of the voice input method, such as high speed, are significantly impaired. In order to solve this problem, Japanese Patent Application Laid-Open No. 56-138799 and other publications provide two signal tones: "beep" and ":f-", so that the voice input in synchronization with the signal tone can be correctly input. It is disclosed that the signal sound is made different depending on whether the signal is recognized or not. According to such means, effects such as being able to prompt the user to re-input voices that are difficult to recognize can be obtained.

However, if things continue as they are, it is unclear how to pronounce them in order for the speech to be recognized correctly, and there is a problem in that there is almost no hope of preventing error 9 from occurring.

[Purpose of the invention]

The present invention has been made in consideration of these circumstances, and its purpose is to easily inform the speaker of the recognition status of input speech and to effectively prevent recognition errors. An object of the present invention is to provide a highly practical speech recognition device capable of speeding up speech input.

[Summary of the invention]

The present invention makes full use of the signal sound that prompts voice input, and changes the output form of the signal sound by changing the frequency, amplitude, duration, etc., depending on the reliability of the voice recognition result. This system informs the speaker of the recognition status of the voice and encourages him or her to make the correct utterance.

〔Effect of the invention〕

Thus, according to the present invention, it is possible to easily improve the accuracy of speech by capturing the recognition status of input speech and the recognition reliability as changes in the signal sound, thereby preventing erroneous recognition and improving the accuracy of speech input. It becomes possible to increase the speed. Moreover, since it is only necessary to vary the signal tone using the recognition reliability, for example, the similarity calculation result in the speech recognition processing process, it is easy to control the signal tone, and it is highly practical. .

[Embodiments of the invention]

Hereinafter, one embodiment of the present invention will be described with reference to the drawings.

Figures 1 (,) to (C) show a signal sound (,) that is output at a predetermined period and prompts voice input, and a voice sound that is input in synchronization with this signal sound (b). ) and the similarity (C) in the above speech recognition process. Here, a change in voice power is shown when a voice such as [o, n, seven, i, two, n, sh, ki] is inputted in synchronization with the signal tone.

FIG. 2 is a schematic configuration diagram of the embodiment device, and 1 is a voice recognition section. This speech recognition unit 1 analyzes the input speech, obtains its speech percentage fine parameters, performs turn matching with the standard speech pattern registered in the dictionary by, for example, calculating the similarity, and calculates the similarity. The above-mentioned input voice is recognized according to the following. In this case, the reliability of recognition is expressed by the degree of similarity determined in the recognition processing process, the difference in degree of similarity between the first and second place, etc. determined in descending order of degree of similarity. However, this reliability information is
Each time one sound is recognized, it is stored in the shift register 2. The similarity averaging circuit 3 obtains the reliability (similarity direct) of the past several samples stored in the shift register 2, averages it, and determines the state of speech recognition. Reliability information indicating the recognition status thus determined is stored in the register 4 as control data.

The signal tone generation circuit 5 is configured so that the voice recognition section 1 recognizes one of the input voices.
In response to a signal output each time a sound recognition process is completed, a signal sound is generated to prompt the speaker to input the next sound. and, .

The output form of this signal sound is variable according to the park opening data stored in the register 4.

The output form of the signal sound is controlled in the following manner. That is, the signal tone is, for example, as shown in FIG.
Threshold 6 for determining the reliability of recognition results is equal to or higher than Th. When accurate speech recognition is being performed, the frequency is controlled to be constant. Then, as the reliability of the voice recognition increases, the signal tone frequency is variably controlled to correspond to the reliability, such as by lowering the frequency. Note that the signal sound may be controlled by, for example, changing the amplitude and output time width of the signal sound depending on the reliability, as shown in FIG. 4, for example. Furthermore, the signal tone output waveform may be distorted to indicate a decrease in reliability. Specifically, if the frequency 'i of the signal sound is changed in a range of 2000 Hz to 1000 Hz, corresponding to a reliability level of 0.1 to 1.0, it can be easily recognized.

In this way, according to this device, in which the form of the signal tone is variably controlled according to the reliability of voice recognition, when the speaker speaks in synchronization with the signal tone, the conventional method of vocalization is not suitable for the device. It is possible to easily know whether the speech is easy to recognize or not, and it becomes possible to immediately input speech that is easy to recognize by the device by devising the method of inputting the speech.

The device can then reliably and reliably recognize this. Therefore, erroneous recognition can be effectively prevented and voice input can be performed quickly and efficiently. Moreover, unlike the conventional signal sound information indicating whether or not recognition has been performed, the recognition status is notified.
It becomes easy to devise vocalizations in order to obtain high recognition accuracy, and it becomes possible to avoid unstable recognition determination processing. Further, as described above, since variable control of the output form of the signal tone is simple, effects such as the ability to manufacture the device easily and at low cost can be achieved.

Note that the present invention is not limited to the above embodiments. For example, the signal sound can be divided into several stages depending on the reliability, and the variable side (
It is also possible to do so. Further, as the reliability information, other judgment factors used in speech recognition processing may be used, and it is also possible to map this to the reliability.

In short, the present invention can be implemented with various modifications without departing from the gist thereof.

[Brief explanation of the drawing]

FIG. 1 is a diagram showing the relationship between signal tones, input voices, and the reliability of their recognition results, FIG. 2 is a schematic configuration diagram of an apparatus according to an embodiment of the present invention, and FIGS. 3 and 4 are respectively for signal tones. FIG. 3 is a diagram showing the relationship between output format and reliability. DESCRIPTION OF SYMBOLS 1...Speech recognition unit, 2...Register, 3...Similarity averaging circuit, 4...Register, 5...Signal sound generation circuit. Applicant's agent Patent attorney Takehiko Suzue 9- Figure J

Claims (2)

[Claims] (1) A means for prompting voice input by outputting a full signal tone, a means for recognizing and processing the voice signal input in synchronization with the signal tone, and a recognition result of the voice signal recognized by this means. 1. A speech recognition device comprising: means for extracting reliability information of the signal sound and varying the output form of the signal tone in accordance with the reliability of the preceding recognition result. (2) The output form of the signal sound is variably set by changing the signal sound frequency, amplitude, signal sound output time width, or signal sound wave shape according to the reliability. Speech recognition device.