Acoustic modeling method and device, and speech recognition method and device

A modeling method and speech recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of difficult recognition effect, degradation of speech data recognition performance, poor speech data recognition effect, etc., to improve robustness, Identifying the effect of improved performance

Inactive Publication Date: 2014-01-15
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF8 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method does not perform well in the recognition of speech data in complex noise environments.
[0005] At present, the existing speech recognition system has better recognition performance for speech data in a quiet environment, but the recognition performance for speech data in a noisy environment is significantly reduced
For voice input and search systems, the input voice noise is complex and changeable, and because tasks such as voice input and search require real-time voice recognition, it is difficult for existing voice recognition methods to achieve good recognition results

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
  • Acoustic modeling method and device, and speech recognition method and device
  • Acoustic modeling method and device, and speech recognition method and device
  • Acoustic modeling method and device, and speech recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0040] figure 1 It is a schematic configuration diagram showing the acoustic modeling device according to Embodiment 1 of the present invention.

[0041] like figure 1 As shown, the acoustic modeling device 100 includes an acquisition unit 101 , a detection and interception unit 102 , a screening unit 103 , a stitching unit 104 , a noise addition processing unit 105 and a modeling unit 106 .

[0042]The collection unit 101 is used to collect a large amount of non-standard corpus in various noise environments to form a non-standard corpus set. Here, non-standard corpus refers to speech data collected in various noise environments in actual work. For example, a speech clip recorded in a university lecture hall; a conversation recorded in a vehicle; voice data randomly recorded on the street, etc. The non-standard corpus is pure speech data, which includes noise as the background and speech as the main body. The non-standard corpus collection refers to the collection of a lar...

Embodiment approach 2

[0064] Embodiment 2 is an example of applying the acoustic modeling method and device of Embodiment 1 to a voice input and search system.

[0065] image 3 It is a schematic configuration diagram showing the speech recognition device 200 according to Embodiment 2 of the present invention.

[0066] like image 3 As shown, the speech recognition device 200 includes a receiving unit 201 , a selection unit 202 , an acoustic modeling device 100 , a recognition unit 203 , a search unit 204 and an output unit 205 .

[0067] The voice recognition device 200 is a voice recognition device used in a voice input and search system in a noisy environment. Moreover, the speech recognition device 200 performs speech recognition by utilizing the acoustic model of the noised corpus established by the acoustic modeling device 100 .

[0068] The receiving unit 201 receives voice information input by a user.

[0069] The modeling unit 106 of the acoustic modeling device 100 includes multiple a...

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 an acoustic modeling method used for speech inputting in a noise environment. The acoustic modeling method includes the following steps that a pure noise section is used for conducting noise adding treatment on standard linguistic data in a standard linguistic data set so that noise adding linguistic data can be formed; acoustic model training is carried out by the way of using the noise adding linguistic data, and an acoustic model of the noise adding linguistic data is established. The invention further provides an acoustic modeling device used for speech inputting in the noise environment and a speech recognition method and device used for speech inputting and system searching in the noise environment. By means of the acoustic modeling method and device, and the speech recognition method and device, the accuracy and the efficiency of speech recognition in the noise environment can be improved.

Description

technical field [0001] The invention relates to a speech recognition technology used in a noisy environment, in particular to an acoustic modeling method and device for speech input in a noisy environment, and a speech recognition method and device. Background technique [0002] The performance of a speech recognition system is affected by many factors, including different speakers, speaking styles, environmental noise, transmission channel, and so on. In order to improve the performance of the speech recognition system, its solutions are divided into two categories according to the method of speech features (hereinafter referred to as feature method) and the method of model adjustment (hereinafter referred to as model method). The former needs to find better and highly robust feature parameters, or add some specific processing methods based on the existing feature parameters. The latter is to use a small amount of adaptive corpus to modify or transform the original acousti...

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): G10L15/06
Inventor 苏丹贾磊
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