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

Distributed voice retrieval system

A retrieval system and distributed technology, applied in speech analysis, speech recognition, special data processing applications, etc., can solve the problem that speech retrieval cannot be accurately matched

Inactive Publication Date: 2013-07-03
大连天维科技有限公司
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, content-based speech retrieval still has the problem of being unable to accurately match

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
  • Distributed voice retrieval system
  • Distributed voice retrieval system
  • Distributed voice retrieval system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] like Figure 1 to Figure 3 The distributed speech retrieval system shown is divided into the following modules:

[0014] The voice cache retrieval server; the voice cache retrieval server is responsible for retrieving the voice cache, and updating the number of visits of keywords in the cache. The most frequently used keywords are stored in the voice cache. Initially, the speech buffer is empty. After the user sends a retrieval request, the retrieval of the voice cache is performed first. If the keyword fields of some entries in the cache match the user's retrieval condition keywords, then these entries are returned to the user, and the access count fields of these entries are updated. If there is no entry in the voice cache that matches the keywords of the user's search criteria, the voice optimization database will be searched. At the same time, insert the keyword that cannot be retrieved in the cache into the queue table.

[0015] The voice optimization retrieva...

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 discloses a distributed voice retrieval system which is characterized by comprising a voice cache retrieving server responsible for retrieving voice cache and updating visited frequency of key words in the cache, an optimized voice retrieving server and a voice spell map retrieving server, wherein key words mostly used by users are stored in the voice cache; optimal spell character strings are stored in the data base of the optimized retrieving server; and spelling map information of a voice file is stored in the data base of the voice spell map retrieving server. The system has the characteristics of simple structure, high processing speed, excellent treating effect and the like.

Description

technical field [0001] The invention relates to a distributed voice retrieval system. Background technique [0002] It is necessary to use a computer to process human voices and background music appearing in video programs, and convert them into character strings or mathematical forms with certain meanings. Usually, the voice information is converted into a pinyin map. By performing a search on the pinyin map, it is possible to obtain those words that may appear in this speech and the probability of these words appearing. Pinyin strings are used as search criteria for searching Pinyin maps. For music, the melody of music can also be obtained by analyzing its waveform characteristics. The data obtained after processing by the above means is called feature data of speech. The amount of feature data is often very large. When conducting content-based speech retrieval, it often faces the problems of huge data volume and low retrieval efficiency. Something must be done. Or ...

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): G06F17/30G10L15/08
Inventor 李丕
Owner 大连天维科技有限公司
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