Unlock instant, AI-driven research and patent intelligence for your innovation.

Voice packet identification

A voice and grouping technology, applied in voice analysis, instruments, etc., can solve problems such as incorrect eigenvectors, difficulties in real-time voice analysis, and long time

Inactive Publication Date: 2007-10-10
INT BUSINESS MASCH CORP
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In particular, if packets are lost, the decompressed waveform will be distorted, the resulting eigenvectors will be incorrect, and the analysis will degrade significantly
Also, the time to obtain the eigenvectors for analysis can be very long due to decompression - FFT - Mel scale filter - cosine transform (see Reynolds et al. above)
This will make real-time voice analysis very difficult

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 packet identification
  • Voice packet identification
  • Voice packet identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Although in accordance with at least one presently preferred embodiment of the present invention generally envisages an apparatus for performing speech signal analysis generally from its compressed domain, particularly advantageous results are obtained in analyzing signals compressed by the CELP algorithm.

[0024] In fact, modern voice compression is often based on CELP algorithms, eg, G723, G729, GSM. (See, e.g., Lajos Hanzo, et. al. "Voice Compression and Communications" John Wiley & Sons, Inc., Publication, ISBN 0-471-15039-8.) Basically, the algorithm models a person's vocal tract The modulus is a set of filter coefficients, and the vocalization is the result of a set of excitations passing through the modeled vocal tract. The pitch of the voice is also captured. According to at least one presently preferred embodiment of the present invention, analyzing packets compressed by the CELP algorithm has very favorable results.

[0025] By way of illustrative and non-l...

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

Mechanisms, and associated methods, for conducting voice analysis (e.g., speaker ID verification) directly from a compressed domain of a voice signal. Preferably, the feature vector is directly segmented, based on its corresponding physical meaning, from the compressed bit stream.

Description

[0001] This invention was made with United States Government support under Contract No: H9823004-3-0001 awarded by the Distillery Phase II Program. The US Government has certain rights in this invention. technical field [0002] The present invention relates generally to speech signal generation and processing. Background technique [0003] Usually, in speech signal generation and processing, the speech signal not only conveys the speech content, but also reveals some information about the identity of the speaker. In this regard, by analyzing the voice signal waveform, one can classify the voice signal into various categories such as speaker ID, language ID, intense voice pitch, and topic. [0004] Conventionally, speech analysis is performed directly on the speech signal waveform. For example, for a conventional speaker ID verification system such as that shown in Figure 1, the speech input 102 is first Fourier transformed into the frequency domain. After spectral energy...

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): G10L17/00
CPCG10L17/00
Inventor D·萨哈Z-Y·谢
Owner INT BUSINESS MASCH CORP