Speech processing method and device, and device for speech processing

A voice processing and voice technology, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as incomplete text information, and achieve the effect of improving accuracy and integrity

Active Publication Date: 2017-07-21
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF7 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

I can’t sit still all the time, hehe, being a good friend with the little chair is the greatest wish of the teacher and parents now.” However, in practical applications, some factors may cause the text in...

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
  • Speech processing method and device, and device for speech processing
  • Speech processing method and device, and device for speech processing
  • Speech processing method and device, and device for speech processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] refer to figure 2 , which shows a flow chart of the steps of Embodiment 1 of a speech processing method of the present invention, which may specifically include the following steps:

[0074] Step 201, after performing a voice transcription for the voice stream, according to the processing result returned by the server for the voice data packets in the voice stream, obtain the target voice data that needs to be re-transcribed from the voice data packets in the voice stream package; wherein, the processing results may include: speech recognition results and / or error codes;

[0075] Step 202, resending the target voice data packet to the server, so that the server performs voice recognition on the target voice data packet;

[0076] Step 203, receiving the voice recognition result returned by the server for the target voice data packet;

[0077] Step 204: Supplement the speech recognition result corresponding to the target speech data packet to the speech transcription r...

Embodiment 2

[0106] refer to image 3 , shows a flow chart of the steps of Embodiment 2 of a speech processing method of the present invention, and this embodiment is figure 2 An optional embodiment of the illustrated embodiment may specifically include the following steps:

[0107] Step 301, in the process of performing a voice transcription for the voice stream, determine the text stream corresponding to the voice stream according to the processing result returned by the server for the voice data packets in the voice stream;

[0108] Step 302, in response to a mark adding instruction triggered by the user, respectively add corresponding marks to the voice stream and its corresponding text stream;

[0109] Step 303, after performing a voice transcription for the voice stream, according to the processing result returned by the server for the voice data packets in the voice stream, obtain the target voice data that needs to be re-transcribed from the voice data packets in the voice stream...

Embodiment 3

[0119] refer to Figure 4 , shows a flow chart of the steps of Embodiment 3 of a speech processing method of the present invention, and this embodiment is figure 2 or image 3 An optional embodiment of the illustrated embodiment may specifically include the following steps:

[0120] Step 401, in the process of voice transcribing for the voice stream, display the text stream corresponding to the voice stream on the playback editing interface according to the processing result returned by the server for the voice data packets in the voice stream;

[0121] Step 402: After one voice transcription of the voice stream is completed, in response to the summary processing command triggered by the user for the text in the playback editing interface, set the target text corresponding to the summary processing command as the text corresponding to the voice stream. a summary of the document;

[0122] Step 403, after performing a voice transcription for the voice stream, according to th...

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 embodiments of the invention provide a speech processing method and a device, and a device for speech processing. The method comprises the following steps: after one speech transcription operation on a speech stream, acquiring a target speech data packet needing to be re-transcribed from the speech data packets in the speech stream according to a processing result of the speech data packets in the speech stream returned by a server, wherein the processing result includes a speech recognition result and/or an error code; resending the target speech data packet to the server to enable the server to recognize speech from the target speech data packet; receiving a speech recognition result returned by the server for the target speech data packet; and adding the speech recognition result corresponding to the target speech data packet to a speech transcription result corresponding to the speech stream. According to the embodiments of the invention, the integrity of the speech transcription result corresponding to the speech stream is improved, and the accuracy of speech transcription is improved.

Description

technical field [0001] The invention relates to the technical field of speech processing, in particular to a speech processing method and device, and a speech processing device. Background technique [0002] In the field of speech processing technology, in some application scenarios, it is necessary to convert speech into text in real time. For example, in a speech input scenario, an input method program can convert the speech input by a user into text in real time. [0003] The process of converting speech into text in real time in existing solutions may include: the client sends a real-time collected speech stream to the server, the server processes the received speech stream, and returns the text corresponding to the processed speech stream to the client information, and the client can display the text information corresponding to the voice stream on the screen in real time, thereby realizing the synchronization of the text information and the voice stream. [0004] In t...

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): G10L15/30G10L15/26
CPCG10L15/26G10L15/30
Inventor 牛露云李洋周麒麟
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap