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

Method and system for reducing time delay of speech recognition system

A speech recognition and system delay technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as low delay, affecting user experience, easy sentence breaks, etc., to reduce delay, improve user experience, and eliminate delay effect of influence

Pending Publication Date: 2020-11-24
BEIJING UNISOUND INFORMATION TECH +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The larger the threshold, the higher the delay; the smaller the threshold, the lower the delay, but it is also easy to break the sentence on the adjacent voice, and the user breaks the sentence after taking a short breath, which affects the user experience

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
  • Method and system for reducing time delay of speech recognition system
  • Method and system for reducing time delay of speech recognition system
  • Method and system for reducing time delay of speech recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0049] The embodiment of the present invention provides a method for reducing the delay of the speech recognition system, such as figure 1 As shown, the method performs the following steps:

[0050] Step 1: Decoding the received voice signal to obtain decoded voice data;

[0051] Step 2: Comparing the audio segment similarity between a certain silent segment in the decoded voice data and the currently received voice segment, to obtain a segment similarity result;

[0052] Step 3: Obtain sentence segmentation results according to the segment similarity results.

[0053] The working principle of the above technical solution is: using the mute feature decoded in the ...

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 method and system for reducing time delay of a speech recognition system, and the method comprises the following steps: 1, decoding a received speech signal to obtain decodedspeech data; 2, comparing the audio clip similarity between a certain mute clip in the decoded speech data and a currently received speech clip to obtain a clip similarity result; and 3, obtaining a sentence segmentation result according to the clip similarity result. According to the method, mute features decoded in an engine are utilized; according to the audio clip similarity between the certain mute clip and the currently received voice clip, the sentence segmentation result is obtained; whether the latest data in the engine has enough long mute clip or not can be monitored in real time, the time delay influence caused by cached data and fragments can be eliminated, and the sentence segmentation signal can be obtained at the first time, so that the user experience can be remarkably improved.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to a method and system for reducing the time delay of a speech recognition system. Background technique [0002] In real-time interaction, the delay of the speech recognition system is an important factor affecting the interactive experience. Lower delay means faster system response and better experience. In the current speech recognition system on the market, the delay includes the inherent delay of the engine and other delays. The inherent delay of the engine means that due to the characteristics of the neural network structure itself, the processing of the engine will always have some unprocessed cached data. Delay; other delays refer to delays other than the inherent delay of the engine, including fragmentation delay and threshold delay. At the beginning and end of the speech, different segment sizes may lead to completely different sentence segmentation effects. 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): G10L15/04G10L15/10G10L19/00G10L25/78
CPCG10L15/04G10L15/10G10L25/78
Inventor 范红亮
Owner BEIJING UNISOUND INFORMATION TECH