Audio annotation model training and audio annotation method and device

A technology for labeling models and training methods, applied in audio data retrieval, audio data query, special data processing applications, etc., can solve problems such as insufficient accuracy and limitations, and achieve the effect of simplifying training steps and improving training efficiency

Pending Publication Date: 2021-08-03
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing technology has problems of insufficient accuracy and limitations when mining speech recognition badcase

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
  • Audio annotation model training and audio annotation method and device
  • Audio annotation model training and audio annotation method and device
  • Audio annotation model training and audio annotation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0020] The traditional speech recognition model mainly includes three parts: decoder, acoustic model and language model. For the audio input by the user, the decoder combines the acoustic model features and language model features to expand the possible recognition paths in the decoding space, and finally selects the path with the highest feature scoring result as the f...

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 an audio annotation model training and audio annotation method, and relates to the technical field of deep learning and voice processing. The audio annotation model training method comprises the following steps: according to a first query log, obtaining a plurality of target audios and query word pairs of the target audios; according to the recognition query words and the modification query words in the query word pairs of the multiple target audios, obtaining the features of the multiple target audios; and determining labels of a plurality of target audios, and training a neural network model by using the features of the plurality of target audios and the labels of the plurality of target audios to obtain an audio labeling model. The audio annotation method comprises the following steps: acquiring an audio to be annotated and a query word pair of the audio to be annotated according to a second query log; according to the recognition query word and the modification query word in the query word pair, obtaining features of the to-be-labeled audio; and inputting the features of the to-be-labeled audio into the audio labeling model, and taking an output result of the audio labeling model as a labeling result of the to-be-labeled audio.

Description

technical field [0001] The present disclosure relates to the technical field of data processing, in particular to the technical fields of deep learning and speech processing. Provided are a method, device, electronic device, and readable storage medium for training an audio tagging model and audio tagging. Background technique [0002] With the rapid development of voice recognition technology, more and more users use voice input to perform queries. However, when the current speech recognition model recognizes the query audio input by the user, it may produce a recognition result with a poor recognition effect, that is, a bad case of speech recognition. These speech recognition badcases are of great significance for optimizing the speech recognition model. However, the existing technology has the problem of insufficient accuracy and limitations when mining speech recognition badcases. Contents of the invention [0003] According to the first aspect of the present disclo...

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): G06F16/63G06F16/683
CPCG06F16/63G06F16/683
Inventor 辛洪生蒋正翔
Owner BEIJING BAIDU NETCOM SCI & TECH 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