Supercharge Your Innovation With Domain-Expert AI Agents!

Acoustic model training method and device, terminal equipment and storage medium

A training method and acoustic model technology, applied in the field of signal processing, can solve problems that affect the accuracy of acoustic model recognition and sound quality, and achieve the effect of reducing demand and improving similarity

Pending Publication Date: 2021-08-31
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present application provides an acoustic model training method, device, terminal equipment and storage medium to solve the problem that the existing acoustic model affects the recognition accuracy and sound quality of the acoustic model due to the poor quality of the data set

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
  • Acoustic model training method and device, terminal equipment and storage medium
  • Acoustic model training method and device, terminal equipment and storage medium
  • Acoustic model training method and device, terminal equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0032] It is to be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described feature, integer, step, operation, element and / or component, but does not exclude one or more other The presence or addition of features, integers, steps, operations, elements, components and / or sets thereof.

[0...

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 is suitable for the technical field of signal processing and provides an acoustic model training method and device, terminal equipment and a storage medium. The method comprises steps of n statement vectors of training voice being extracted through a statement coding module to obtain statement features of the training voice; extracting n segments of phoneme vectors of the training voice through a phoneme coding module to obtain phoneme features of the training voice; inputting the n statement vectors and the n segments of phoneme vectors into an acoustic modeling module to obtain the acoustic information of the training voice; and inputting the acoustic information of the training voice into a decoding module to obtain a spectrogram of the training voice. According to the training voice and the spectrogram of the training voice, the parameters of the decoding module are updated, rich fine-granularity acoustic information can be captured from the training voice, the demand of the training voice is reduced, acquisition difficulty of a data set is reduced, and the quality of the data set is improved; and thus, naturalness of speech synthesis and similarity between the speech synthesis and the speaker sound are improved.

Description

technical field [0001] The present application belongs to the technical field of signal processing, and in particular, relates to an acoustic model training method, apparatus, terminal device and storage medium. Background technique [0002] Speech synthesis can convert text into corresponding speech, and has been widely used in smart mobile terminals, smart homes, smart robots, and in-vehicle equipment. A speech synthesis system usually includes an acoustic model and a language model. The acoustic model is used to extract the acoustic information of speech to form a spectrogram, and the language model is used to form a corresponding text according to the spectrogram. After the speech synthesis meets the basic requirements of clear voice, the development focus shifts to improving the naturalness of speech synthesis and the similarity with the speaker's voice, which puts forward further requirements for the performance of the acoustic model. [0003] In order to improve the ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G10L13/08G10L25/30
CPCG10L13/08G10L25/30
Inventor 郭洋王健宗
Owner PING AN TECH (SHENZHEN) CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More