Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A combined modeling method of speech recognition and synthesis for edge devices

A speech recognition and edge device technology, applied in the field of speech recognition-synthesis joint modeling, can solve problems such as lack of model performance, loopholes in the operation process, poor input data characteristics, etc., to achieve rich creativity, robust performance, and rich functions Effect

Active Publication Date: 2022-07-01
NORTHWEST UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The reasons are mostly poor input data characteristics, lack of performance of the model itself, and loopholes in the operation process.

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
  • A combined modeling method of speech recognition and synthesis for edge devices
  • A combined modeling method of speech recognition and synthesis for edge devices
  • A combined modeling method of speech recognition and synthesis for edge devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention is further described below in conjunction with accompanying drawing and embodiment, but the present invention is not limited to following embodiment:

[0030] like figure 1 , 2 , 3, an edge device-oriented speech recognition-synthesis joint modeling method, including the following steps:

[0031] 1) Collect dataset samples. Divided into a. clean audio in a quiet environment b. different types of noise audio (specifically: white noise, pink noise, speech babble, etc., refer to the noise noise library for classification) All audio data is a sampling rate of 16k, and the storage format is pcm ( Shaanxi, Minnan, Changsha, Sichuan, Hebei, Shanghai six dialects);

[0032] 2) Carry out data processing. First, do noise fusion processing, add noise to clean audio, package and assemble into clean audio and the corresponding noise-added frequency;

[0033] 3) Build an edge server, perform audio front-end processing on this layer of equipment for de-rever...

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

A combined modeling method of speech recognition-synthesis for edge devices, through the research on real-time computing, the distribution of edge computing strategies and the inspiration of "copy without aliasing" in entertainment games, the back-end integrates speech recognition and speech synthesis technology. Model iteration method. Based on the speech enhancement function in the field of audio processing, a real-time and efficient processing module is constructed, and an iterative model of speech recognition and synthesis for Chinese dialects is constructed based on speech recognition technology and speech synthesis technology. The real-time dialect processing model based on the real-time dialect processing model effectively utilizes the richer processing capabilities of the edge environment, combines speech recognition and speech synthesis technologies, and designs a speech model with richer functions and more robust performance.

Description

technical field [0001] The invention belongs to the technical fields of edge computing and audio research, relates to edge servers, speech enhancement, speech recognition, speech synthesis, and neural networks, and in particular relates to an edge device-oriented speech recognition-synthesis joint modeling method. Background technique [0002] After Industry 4.0, the rapid rise of artificial intelligence and the Internet of Things (IoT) has provided great potential for the convenience of human beings in terms of clothing, food, housing and transportation, and many smart products have emerged as the times require. At the same time, with the development of edge computing in recent years, the edge computing strategy can effectively realize the distribution of large-scale tasks, solve real-time problems, and improve the calculation ability of the model. Therefore, it provides infinite possibilities for continuously strengthening and expanding the functions of smart products. ...

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 Patents(China)
IPC IPC(8): G10L13/02G10L13/04G10L15/02G10L15/06G10L15/26G10L25/24G10L25/30
CPCG10L13/02G10L13/04G10L15/02G10L15/063G10L15/26G10L25/24G10L25/30
Inventor 王海秦晨光张晓刘艺赵子鑫高岭任杰郑杰
Owner NORTHWEST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com