Voice endpoint detection method based on waveform morphological characteristic clustering

A technology of morphological features and endpoint detection, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as complex calculation process

Active Publication Date: 2014-01-01
ZHEJIANG UNIV
View PDF5 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The disadvantage of this method is that it needs to obtain multip

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 endpoint detection method based on waveform morphological characteristic clustering
  • Voice endpoint detection method based on waveform morphological characteristic clustering
  • Voice endpoint detection method based on waveform morphological characteristic clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The endpoint detection of the present invention based on waveform morphological feature clustering into five parts will be described in detail below with reference to the accompanying drawings and embodiments.

[0027] The experimental data of the present embodiment of the present invention is the telephone data in the train part and the test part in the male of NIST Speaker Recognition Evaluation evaluation in 2004, 2006 and 2008, the telephone data in the train in 2004 included 248 voices, and the telephone data in the test Contains 1606 voices; the telephone data in the train in 2006 contains 354 voices; and the telephone data in the train in 2008 contains 648 voices. NIST provided correct endpoint text information for all speech data in 2004 and 2006, so it can be used to detect the error rate of the present invention. In the following, male_train_telephone is used to represent the telephone data in the train part of male, and male_test_telephone is used to represen...

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 a voice endpoint detection method based on waveform morphological characteristic clustering. The voice endpoint detection method based on waveform morphological characteristic clustering includes the following steps that first, a pure voice signal is acquired through an original voice signal; second, an envelope signal of the pure voice signal is acquired and divided into a plurality of voice sub-segments; third, according to the waveform morphological characteristics of all the voice sub-segments, the voice sub-segments are clustered and non-voice voice sub-segments are removed; fourth, all the voice sub-segments of reserved parts in the third step are processed, and a voice endpoint is obtained. According to the method, a good result can be obtained fast and accurately with a relative simple non-monitoring clustering method under the condition that a single characteristic is utilized.

Description

technical field [0001] The invention relates to the field of voice endpoint detection, in particular to a voice endpoint detection method based on waveform morphological feature clustering. Background technique [0002] The current development of voiceprint recognition technology has reached a relatively high level, and speech endpoint detection is a necessary step in speech analysis, speech synthesis and speaker recognition. In speech repetition systems and speech recognition systems, speech endpoint detection technology has achieved A relatively good result has been obtained. There are many existing endpoint detection technologies. The main features used are short-term energy, zero-crossing rate, information entropy, subband energy, pitch, time domain parameters, frequency domain parameters, and cepstrum parameters. And so on, and the model classification methods used are also various, mainly including double threshold, neural network, wavelet model, hidden Markov model, e...

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
IPC IPC(8): G10L25/78G10L15/20G10L21/0208
Inventor 杨莹春赵启明吴朝晖
Owner ZHEJIANG UNIV
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