Speech and noise models for speech recognition

A technology of speech model and noise model, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as difficulty in accurately recognizing spoken utterances

Active Publication Date: 2013-04-24
GOOGLE LLC
View PDF5 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Ambient audio may partially obscure the user's voice, making it difficult for an automated speech recognition ("ASR") engine to accurately recognize spoken words

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 and noise models for speech recognition
  • Speech and noise models for speech recognition
  • Speech and noise models for speech recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] figure 1is a schematic diagram illustrating an example of a system 100 that supports voice search queries. System 100 includes a search engine 106 and an Automatic Speech Recognition (ASR) engine 108, which are connected to a set of mobile devices 102a-102c and mobile device 104 through one or more networks 110, such as in some embodiments, the one or The plurality of networks 110 is a wireless cellular network, a wireless local area network (WLAN) or a Wi-Fi network, a third generation (3G) mobile telecommunications network, a private network such as an intranet, a public network such as the Internet, or any suitable combination thereof.

[0025] Typically, a user of a device such as mobile device 104 can dictate a search query into the microphone of mobile device 104 . An application running on the mobile device 104 records the user's spoken search query as an audio signal and sends the audio signal to the ASR engine 108 as part of the voiced search query. After re...

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

An audio signal generated by a device based on audio input from a user may be received. The audio signal may include at least a user audio portion that corresponds to one or more user utterances recorded by the device. A user speech model associated with the user may be accessed and a determination may be made background audio in the audio signal is below a defined threshold. In response to determining that the background audio in the audio signal is below the defined threshold, the accessed user speech model may be adapted based on the audio signal to generate an adapted user speech model that models speech characteristics of the user. Noise compensation may be performed on the received audio signal using the adapted user speech model to generate a filtered audio signal with reduced background audio compared to the received audio signal.

Description

[0001] Cross References to Related Applications [0002] This application claims priority to US Application Serial No. 12 / 814,665, filed June 14, 2010, and entitled "SPEECH ANDNOISE MODELS FOR SPEECH RECOGNITION," the disclosure of which is incorporated herein by reference. technical field [0003] This manual deals with speech recognition. Background technique [0004] Speech recognition can be used for voice search queries. Typically, a search query includes one or more query terms submitted by a user to a search engine when the user requests the search engine to perform a search. In other ways, a user may enter the query terms of a search query by typing on a keyboard or, in the case of a voice query, by dictating the query terms into, for example, a mobile device's microphone. [0005] When a voice query is submitted through, for example, a mobile device, the mobile device's microphone may record ambient noise or sounds, otherwise known as "ambient audio" or "backgrou...

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): G10L15/20
CPCG10L21/0208G10L15/20
Inventor M·I·洛伊德T·克里斯特詹森
Owner GOOGLE LLC
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