JPS61138998A - Voice data storage reproducer - 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] [Industrial usage total] The present invention relates to an audio data storage and playback device.

[Conventional technology]

This audio data storage and playback device breaks down audio into syllables,
It is encoded into syllables and converted into data characters, which are then stored.

[Problem that the invention seeks to solve]

Conventional audio data storage and playback devices of this type cannot distinguish between speakers, timbres of voices, intonations of voices, etc. because data characters cannot define attributes of voices.

[Means for solving problems]

The present invention, along with a data string encoded from syllables,
The above problem is solved by simultaneously creating control characters that define the attributes of the voice, and defining the attributes of the voice, such as timbre, intonation, pitch, etc., using the control characters.

That is, the data storage and playback device according to the present invention includes a speech recognition device that recognizes human speech in units of syllables and separates it into syllables and control characters, a syllable conversion device that converts the syllables into data character strings, and a data character string. Accumulate the column and the control character
The apparatus includes a storage and playback device for playback, a data conversion device for converting the data character string into syllables, and a loud voice synthesis device for synthesizing output speech using the syllables and the control characters.

[Actual example]

Embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram of an embodiment of an audio data storage and playback device according to the present invention.

The voice data storage and playback device of this embodiment is a voice recognition device! 1
1, a syllable converter t2, a speech synthesizer 3, a data converter 4, a g-dan playback device 5, and a signal display device 6.

The speech recognition device 1 that has received the human voice 10 recognizes this input voice 10 in syllable units and decomposes it into stored syllables 20, and at the same time defines the attributes of the input voice 10 in the storage control character 30, and converts the stored syllables 20 into The data is transferred to the syllable conversion device 2, and the storage control characters 30 are transferred to the storage and playback device 5.

The syllable conversion device ff12 that has received the stored syllable 20 converts the stored syllable 20 into a uniquely determined coded stored data character string 40, and transfers it to the #dan\ playback device 5.

The storage/playback device 5 that has received the storage control character 80 and the storage data character string 40 combines the storage control character 30 and the storage data character string 40 and stores the combination as one word 45 for four characters.

The signal processing device 6 processes the accumulation control characters 30 that compose the accumulation signal 45 using the processing signal 90, processes the attributes of the accumulation signal 45, and converts it into a reproduction fi number 65. Note that there are cases in which processing, ie, conversion, by the signal processing device 16 is not performed.

The storage/playback device 5 decomposes the playback signal 65 into a playback control character 60 defining the attributes of the playback signal 65 and a playback data string 80, and converts the playback control character 60 into a speech synthesis device t8.
The playback data character string 80 is transferred to the data conversion device 4.

The data conversion device 4 that has received the reproduction data character string 80 converts the uniquely encoded reproduction data character string 8o into a corresponding reproduction syllable 7o.

Playback sound II! 170 and the reproduction control character 60, the speech synthesis device 18 resynthesizes the reproduced sound m70 into the output voice 50 based on the reproduction control character 60 defining the attribute.

〔Effect of the invention〕

As explained above, the present invention makes it possible to reproduce the characteristics of speech by decomposing speech into control characters that define the attributes of the speech and data strings corresponding to syllables, storing and reproducing them. However, it is possible to store data using a storage device with a smaller storage capacity than before, and it is also possible to differentiate between multiple speakers, voice timbre, and intonation, and it is also possible to use control characters that define voice attributes. By processing, it becomes possible to convert the attributes of the reproduced audio.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing an embodiment of an audio data storage and playback device according to the present invention. 1: Speech, @ recognition device, 2: Syllable conversion device. 3: Speech synthesis device, 4: Data conversion device. 5: Storage and regeneration device, 6: [δ No. 1 immediate production device. lO: human speech, 20: stored syllables. 3o: Type 4 control character, 40: #dan data character string. 50: Output audio, 60s: Playback control characters. 70: Playback syllable, 80 = Playback data character string. 90: Processing signal, 45: Accumulation signal. 65: Reproduction signal.

Claims (1)

[Scope of Claims] A speech recognition device that recognizes input speech syllable by syllable and separates it into syllables and control characters; a syllable conversion device that converts the syllables into a data string; and the data string and the control characters. a storage and playback device that stores and plays back the data; a data conversion device that converts the data character string into syllables; and a speech synthesis device that synthesizes output speech using the syllables and the control characters. playback device.