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

A Streaming Speech Recognition Method

A speech recognition and streaming technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of low number of concurrently recognized audio streams and consumption of computing resources, and achieve the effect of avoiding resource consumption and reducing computing resources

Active Publication Date: 2022-04-22
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this way, the number of audio streams that can be recognized concurrently by each engine is not high. For a product with tens of thousands of concurrent live broadcasts, if you want to cover and recognize all live streams, it will cause a lot of computing resource consumption.

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 Streaming Speech Recognition Method
  • A Streaming Speech Recognition Method
  • A Streaming Speech Recognition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

[0051]The terminology used in the present disclosure is for the purpose of describing particular embodiments only, and is not intended to limit the present disclosure. As used in this disclosure and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood ...

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 disclosure provides a streaming speech recognition method. On the one hand, the speech segment to be detected is sent to the speech endpoint detection end, and the silent data in the speech segment to be detected is extracted according to the returned result, and only valid speech data is retained for recognition, reducing the required computing resources for speech recognition. On the one hand, the unfinished segment at the end of each segment of speech is stored in the state database, so that the state database is used as a context state storage device for multiple speech segments, further avoiding resource consumption caused by the speech recognition engine maintaining audio stream context data, and maintaining state The problem of poor scalability and reduced reliability brought by information.

Description

technical field [0001] The present disclosure relates to the technical field of speech recognition, in particular to a streaming speech recognition method. Background technique [0002] With the development of mobile Internet and multimedia technology, there are more and more product forms that include audio streaming, such as common live broadcast applications and voice chat room applications. Perform speech recognition on audio streams (streaming speech), and the text results obtained after recognition are very important for content security review, content analysis and labeling, etc. [0003] In a traditional solution, when performing speech recognition on an audio stream, the client usually sends multiple continuous speech segment data of the audio stream to the speech recognition engine, and the speech recognition engine sequentially recognizes and returns the recognition results. In this way, the number of audio streams that can be recognized concurrently by each engi...

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): G10L15/04G10L15/22G10L15/26
CPCG10L15/04G10L15/22G10L15/26
Inventor 杨德兴
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD