Method and device for acquiring speech training sample

A speech training and sample technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as difficult to guarantee sound quality and influence on model accuracy, achieve natural timbre and sound style, and improve accuracy
CN110473525AActive Publication Date: 2019-11-19BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
6 Cites 12 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Publication Date
2019-11-19

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The embodiment of the invention relates to the technical field of speech synthesis, and discloses a method and a device for acquiring a speech training sample. A specific implementation mode of the method comprises the steps of responding to a detected command for recording user speech corresponding to a target statement, and displaying record reference information of the target statement; recording speech sent by a user according to the record reference information, and obtaining a user record corresponding to the target statement; responding to the circumstance that the quality of the user record corresponding to the target statement is determined to meet the preset speech quality condition; and generating the training sample for training a speech synthesis model according to the user record corresponding to the target statement. According to the method and the device for acquiring the speech training sample provided by the embodiment of the invention, under the circumstance that theuser record meet the preset speech quality condition, through generating the training sample, the follow-up speech synthesis model training is realized, so that the speech synthesis model obtained through training is accurate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical field

[0001] The embodiments of the present disclosure relate to the field of computer technology, in particular to the field of speech synthesis technology, and in particular to a method and device for obtaining speech training samples. Background technique

[0002] Speech synthesis technology is a technology that produces artificial speech through machinery and equipment. A common method of speech synthesis is to use a trained speech synthesis model to synthesize speech. Speech synthesis generally needs to use recorded user voice for training, so that the trained model can generate a voice that is more consistent with the timbre and style of the user's voice.

[0003] In related technologies, the sound quality of the user's recording is usually difficult to guarantee, and the accuracy of the trained model will be affected. Summary of the invention

[0004] The embodiments of the present disclosure propose methods and devices for obtaining speech training samples. [000...

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