Voice activity detection

A technology of voice activity and activity, which is applied in speech analysis, instruments, etc., and can solve the problem that the noise reference is not directly available

Inactive Publication Date: 2013-01-16
QUALCOMM INC
View PDF6 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, a suitable noise reference may not be directly available in these cases, and the noise reference may have to be derived indirectly

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
  • Voice activity detection
  • Voice activity detection
  • Voice activity detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] In speech processing applications (eg, voice communication applications such as telephony), it may be desirable to perform accurate detection on segments of audio signals carrying speech information. Such voice activity detection (VAD) may be important, for example, when preserving voice information. A speech coder (also known as a coder-decoder (codec) or vocoder) is typically configured to allocate more bits to the segment identified as noise than is used to encode the segment identified as noise. Segments of speech are encoded such that misidentification of segments carrying speech information may degrade the quality of that information in decoded segments. In another example, the noise reduction system may aggressively attenuate low-energy unvoiced speech segments if the voice activity detection stage fails to identify these segments as speech.

[0075] Recent attention to wideband (WB) and super wideband (SWB) codecs has emphasized the preservation of high frequen...

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

Implementations and applications are disclosed for detection of a transition in a voice activity state of an audio signal, based on a change in energy that is consistent in time across a range of frequencies of the signal.

Description

[0001] Claim of priority under 35 U.S.C. §119 [0002] This patent application claims No. 61 of the title "Systems, Methods, and Apparatus for Speech Feature Detection (SYSTEMS, METHODS, AND APPARATUS FOR SPEECH FEATURE DETECTION)" filed on April 22, 2010 and assigned to the assignee. Priority to Provisional Application No. / 327,009 (Attorney Docket No. 100839P1). technical field [0003] The invention relates to the processing of speech signals. Background technique [0004] Many activities that used to take place in a quiet office or home environment are now performed in acoustically variable situations such as cars, streets or coffee shops. For example, a person may wish to communicate with another person using a voice communication channel. The channel may be provided, for example, by a mobile wireless handset or headset, walkie-talkie, two-way radio, car kit, or another communication device. Accordingly, a large amount of voice communication is conducted using mobile...

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): G10L25/18G10L25/60G10L25/93
CPCG10L25/78G10L25/93
Inventor 埃里克·维瑟伊恩·埃尔纳恩·刘辛钟元
Owner QUALCOMM INC
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