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

Symmetrical audio acquisition method and device, electronic equipment and storage medium

An acquisition method and audio technology, applied in speech analysis, speech synthesis, instruments, etc., can solve problems such as unstable training of deep learning network models, fluctuating audio volume, asymmetrical voice signal waveforms, etc., to improve the listening experience , reduce the probability of error, and improve the effect of volume consistency

Pending Publication Date: 2022-05-13
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] There is asymmetry in the voice signal waveform in a lot of audio data, which will lead to unstable model training of the deep learning network, and the volume of the generated audio will fluctuate.

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
  • Symmetrical audio acquisition method and device, electronic equipment and storage medium
  • Symmetrical audio acquisition method and device, electronic equipment and storage medium
  • Symmetrical audio acquisition method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0027] In order to facilitate the understanding of the present disclosure, the technical fields involved in the present disclosure are briefly explained below.

[0028] Data processing is the acquisition, storage, retrieval, processing, transformation and transmission of data. Through data processing, it is possible to extract and deduce valuable and meaningful data fo...

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 provides a symmetric audio acquisition method and device, electronic equipment and a storage medium, and relates to the field of data processing, in particular to the field of voice technologies and deep learning. The specific implementation scheme is as follows: acquiring a to-be-processed original audio; performing phase spectrum offset processing on the original audio to generate a plurality of offset audios with offset phases; and performing waveform symmetry detection on the plurality of offset audios, and obtaining a waveform-symmetric target audio from the plurality of offset audios. According to the invention, based on the phase spectrum offset processing, the original audio is processed into the target audio with the symmetrical waveform, so that the volume consistency of the audio signal is greatly improved, stable training of a deep learning network is facilitated, the error probability of speech synthesis is reduced, and the listening experience of a user is improved.

Description

technical field [0001] The present disclosure relates to the field of data processing, in particular to the fields of speech technology and deep learning. Background technique [0002] Many audio data have asymmetric speech signal waveforms, which will lead to unstable model training of the deep learning network, and the volume of the generated audio will fluctuate. Contents of the invention [0003] The present disclosure provides a symmetrical audio acquisition method, device, electronic equipment, storage medium, and computer program product. [0004] According to an aspect of the present disclosure, a method for acquiring symmetric audio is provided, including: [0005] Get the raw audio to be processed; [0006] Perform phase spectrum shift processing on the original audio to generate multiple shifted audio with phase shifted; [0007] Perform waveform symmetry detection on multiple offset audios, and obtain target audio with symmetrical waveforms from multiple off...

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): G10L13/02G10L19/02G10L19/04G10L21/0332G10L25/27
CPCG10L13/02G10L19/0212G10L19/04G10L21/0332G10L25/27
Inventor 刘钊宇
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD