Unlock instant, AI-driven research and patent intelligence for your innovation.

Apparatus and method for creating dictionary for speech synthesis

A technology for making devices and dictionaries, which is applied in speech synthesis, speech analysis, instruments, etc. It can solve problems such as continuous recording, inability to confirm the sound quality of synthesized waveforms, and reduced production efficiency of voice synthesis dictionaries, so as to achieve the effect of improving production efficiency

Inactive Publication Date: 2013-04-03
KK TOSHIBA
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, in the above-mentioned system, it is necessary to record waveforms of voices that read all predetermined sentences aloud in the creation of a speech synthesis dictionary, and it is impossible to check the sound quality of the synthesized waveforms in the middle of recording.
Therefore, even if the sound quality of the synthesized waveform is sufficiently high, the user may continue to record, etc., and there is a problem that the production efficiency of the voice synthesis dictionary is reduced.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Apparatus and method for creating dictionary for speech synthesis
  • Apparatus and method for creating dictionary for speech synthesis
  • Apparatus and method for creating dictionary for speech synthesis

Examples

Experimental program
Comparison scheme
Effect test

no. 1 Embodiment approach

[0016] The synthesized dictionary creating device of the first embodiment is a device that records the voice of a user who reads a sentence, and creates a user-customized voice synthesized dictionary using the recorded waveform. By voice synthesis using the voice synthesis dictionary created by this device, the user can read arbitrary sentences with their own voice quality.

[0017] figure 1 It is a block diagram of the synthesized dictionary creation device 100 of the first embodiment. The synthesized dictionary making device of the present embodiment is provided with: the sentence storage unit 109 that stores predetermined N (N is a natural number, N≥2) sentences; presents to the user the first sentence sequentially selected from the N sentences stored in the sentence storage unit 109 The prompting part 110 of the first sentence; the voice recording of the user who reads the first sentence aloud, and the recording part 101 that stores the recorded waveform in association wi...

no. 2 Embodiment approach

[0083] Figure 5It is a block diagram of the synthesized dictionary creation device 500 of the second embodiment. The difference from the voice synthesis creation device 100 of the first embodiment is that the voice quality evaluation unit 501 evaluates the voice quality of the synthesized waveform based on the similarity between the recorded waveform stored in the recording unit 101 and the synthesized waveform generated by the voice synthesizer 107 .

[0084] Here, the first sentence corresponding to the recorded waveform stored in the storage unit 101 is used as the second sentence in the speech synthesis unit 107 . Then, the degree of similarity between the recorded waveform of the first sentence and the synthesized waveform generated from the second sentence is calculated. In this way, by matching the utterance contents between the recorded waveform and the synthesized waveform, it is possible to evaluate the similarity excluding the difference in utterance contents. Th...

Deformed example 1

[0088] In the speech synthesis dictionary creation device of this embodiment, the user is presented with first sentences sequentially selected from predetermined N4 sentences, but the first sentences presented to the user may be a plurality of sentences. That is, a segment including a plurality of first sentences may be presented to the user. In addition, N sentences may be stored in the sentence storage unit 109 as a segment including a plurality of sentences.

[0089] In addition, in the speech synthesis dictionary creation device of the present embodiment, it is judged whether or not to create a speech synthesis dictionary based on the variable M and the data volume of all recorded waveforms. , The amount of data of all recorded waveforms, and judge whether to make a voice synthesis dictionary. That is, the necessity determination unit 104 determines whether or not to create a speech synthesis dictionary based on the number of first sentences whose recording has been prope...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to an apparatus and a method for creating dictionary for speech synthesis, in order to improve creating efficiency of speech synthesis dictionary. Apparatus for creating dictionary for speech synthesis comprises a presentation unit, a recording unit, a necessity determination unit, a dictionary creation unit and a speech synthesis unit. The presentation unit presents to users first sentences sequentially selected from N sentences (N is natural numbers and not less than 2) stored in a sentence storage unit. The recording unit records each user speech of the first sentences and store recording waveforms with the first sentence in an associated way. The necessity determination unit makes a determination of whether to create the speech synthesis dictionary under a condition that the recording unit store M waveforms of the first sentences (M is natural numbers and 1<=M<N). The dictionary creation unit creates the speech synthesis dictionary when the speech synthesis dictionary is determined to be produced. The speech synthesis unit converts a second sentence to a synthetic waveform with the speech synthesis dictionary.

Description

[0001] References to related applications such as priority basic applications [0002] This application is based on Japanese Patent Application No. 2011-209989 (filing date: September 26, 2011), and enjoys the priority of this application. This application incorporates the entire contents of this application by referring to this application. technical field [0003] Embodiments of the present invention relate to a synthetic dictionary (dictionary) creation device and a synthetic dictionary creation method. Background technique [0004] There is known a speech synthesis technique for converting arbitrary text into a synthesized waveform. In order to reproduce the voice quality of a specific user using voice synthesis technology, it is necessary to record a large amount of the user's voice, and use the recorded waveform to create a voice synthesis dictionary. In order to achieve this object, a system has been proposed in which a user reads a plurality of predetermined senten...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G10L13/02
CPCG10L13/02G10L13/06G10L25/60
Inventor 橘健太郎森田真弘笼岛岳彦
Owner KK TOSHIBA