Voiced/nonvoiced detection based on robustness of voiced epochs
In this paper, a new method for voiced/nonvoiced detection based on epoch extraction is proposed. Zero-frequency filtered speech signal is used to extract the instants of significant excitation (or epochs). The robustness of the method to extract epochs in the voiced regions, even with small amount...
Main Authors: | , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
IEEE
2010
|
Subjects: | |
Online Access: | http://repository.ias.ac.in/57787/ http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5353617 |
id |
ftindianacasci:oai:repository.ias.ac.in:57787 |
---|---|
record_format |
openpolar |
spelling |
ftindianacasci:oai:repository.ias.ac.in:57787 2023-05-15T15:03:29+02:00 Voiced/nonvoiced detection based on robustness of voiced epochs Dhananjaya, N. Yegnanarayana, B. 2010-03 http://repository.ias.ac.in/57787/ http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5353617 unknown IEEE Dhananjaya, N. Yegnanarayana, B. (2010) Voiced/nonvoiced detection based on robustness of voiced epochs IEEE Signal Processing Letters, 17 (3). pp. 273-276. ISSN 1070-9908 QA75 Electronic computers. Computer science Article PeerReviewed 2010 ftindianacasci 2013-01-20T12:06:39Z In this paper, a new method for voiced/nonvoiced detection based on epoch extraction is proposed. Zero-frequency filtered speech signal is used to extract the instants of significant excitation (or epochs). The robustness of the method to extract epochs in the voiced regions, even with small amount of additive white noise, is used to distinguish voiced epochs from random instants detected in nonvoiced regions. The main feature of the proposed method is that it uses the strength of glottal activity as against using the periodicity of the signal. Performance of the proposed algorithm is studied on TIMIT and CMU ARCTIC databases, for two different noise types, white and vehicle noise from the NOISEX database, at different signal-to-noise ratios (SNRs). The proposed method performs similar or better than the popular normalized crosscorrelation based voiced/nonvoiced detection used in the open source utility wavesurfer, especially at lower SNRs. Article in Journal/Newspaper Arctic Indian Academy of Sciences: Publication of Fellows Arctic |
institution |
Open Polar |
collection |
Indian Academy of Sciences: Publication of Fellows |
op_collection_id |
ftindianacasci |
language |
unknown |
topic |
QA75 Electronic computers. Computer science |
spellingShingle |
QA75 Electronic computers. Computer science Dhananjaya, N. Yegnanarayana, B. Voiced/nonvoiced detection based on robustness of voiced epochs |
topic_facet |
QA75 Electronic computers. Computer science |
description |
In this paper, a new method for voiced/nonvoiced detection based on epoch extraction is proposed. Zero-frequency filtered speech signal is used to extract the instants of significant excitation (or epochs). The robustness of the method to extract epochs in the voiced regions, even with small amount of additive white noise, is used to distinguish voiced epochs from random instants detected in nonvoiced regions. The main feature of the proposed method is that it uses the strength of glottal activity as against using the periodicity of the signal. Performance of the proposed algorithm is studied on TIMIT and CMU ARCTIC databases, for two different noise types, white and vehicle noise from the NOISEX database, at different signal-to-noise ratios (SNRs). The proposed method performs similar or better than the popular normalized crosscorrelation based voiced/nonvoiced detection used in the open source utility wavesurfer, especially at lower SNRs. |
format |
Article in Journal/Newspaper |
author |
Dhananjaya, N. Yegnanarayana, B. |
author_facet |
Dhananjaya, N. Yegnanarayana, B. |
author_sort |
Dhananjaya, N. |
title |
Voiced/nonvoiced detection based on robustness of voiced epochs |
title_short |
Voiced/nonvoiced detection based on robustness of voiced epochs |
title_full |
Voiced/nonvoiced detection based on robustness of voiced epochs |
title_fullStr |
Voiced/nonvoiced detection based on robustness of voiced epochs |
title_full_unstemmed |
Voiced/nonvoiced detection based on robustness of voiced epochs |
title_sort |
voiced/nonvoiced detection based on robustness of voiced epochs |
publisher |
IEEE |
publishDate |
2010 |
url |
http://repository.ias.ac.in/57787/ http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5353617 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
Dhananjaya, N. Yegnanarayana, B. (2010) Voiced/nonvoiced detection based on robustness of voiced epochs IEEE Signal Processing Letters, 17 (3). pp. 273-276. ISSN 1070-9908 |
_version_ |
1766335334790987776 |