Time-Order Representation Based Method for Epoch Detection from Speech Signals
Epochs present in the voiced speech are defined as time instants of significant excitation of the vocal tract system during the production of speech. Nonstationary nature of excitation source and vocal tract system makes accurate identification of epochs a difficult task. Most of the existing method...
Published in: | Journal of Intelligent Systems |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
De Gruyter
2012
|
Subjects: | |
Online Access: | https://doi.org/10.1515/jisys-2012-0003 https://doaj.org/article/77b1e5e6cce94890a292f10d9d927d61 |
id |
ftdoajarticles:oai:doaj.org/article:77b1e5e6cce94890a292f10d9d927d61 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:77b1e5e6cce94890a292f10d9d927d61 2023-05-15T15:10:56+02:00 Time-Order Representation Based Method for Epoch Detection from Speech Signals Jain Pooja Pachori Ram Bilas 2012-03-01T00:00:00Z https://doi.org/10.1515/jisys-2012-0003 https://doaj.org/article/77b1e5e6cce94890a292f10d9d927d61 EN eng De Gruyter https://doi.org/10.1515/jisys-2012-0003 https://doaj.org/toc/0334-1860 https://doaj.org/toc/2191-026X 0334-1860 2191-026X doi:10.1515/jisys-2012-0003 https://doaj.org/article/77b1e5e6cce94890a292f10d9d927d61 Journal of Intelligent Systems, Vol 21, Iss 1, Pp 79-95 (2012) speech signal analysis epoch detection pitch frequency estimation voiced detection time-order representation fourier–bessel series expansion Science Q Electronic computers. Computer science QA75.5-76.95 article 2012 ftdoajarticles https://doi.org/10.1515/jisys-2012-0003 2022-12-31T11:39:49Z Epochs present in the voiced speech are defined as time instants of significant excitation of the vocal tract system during the production of speech. Nonstationary nature of excitation source and vocal tract system makes accurate identification of epochs a difficult task. Most of the existing methods for epoch detection require prior knowledge of voiced regions and a rough estimation of pitch frequency. In this paper, we propose a novel method that relies on time-order representation (TOR) based on short-time Fourier–Bessel (FB) series expansion which can be employed on entire speech signal to detect epochs without any prior information. The proposed method automatically detects voiced regions in the speech signal by computing the marginal energy density with respect to time in the low frequency range (LFR) from the energy distribution in the time-frequency plane. An estimate of pitch frequency for each detected voiced region is then obtained by computing the marginal energy density with respect to frequency in the LFR from the energy distribution in the time-frequency plane. Epochs are located for each detected voiced region as peaks in the derivative of the low pass filtered (LPF) signal corresponding to falling edges of peak negative cycles in the LPF signal synthesized from TOR coefficients corresponding to LFR. Experimental results obtained by the proposed method on speech signals taken from the CMU-Arctic database are found to be promising. The proposed method detects epochs with high accuracy and reliability. Article in Journal/Newspaper Arctic Directory of Open Access Journals: DOAJ Articles Arctic Journal of Intelligent Systems 21 1 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
speech signal analysis epoch detection pitch frequency estimation voiced detection time-order representation fourier–bessel series expansion Science Q Electronic computers. Computer science QA75.5-76.95 |
spellingShingle |
speech signal analysis epoch detection pitch frequency estimation voiced detection time-order representation fourier–bessel series expansion Science Q Electronic computers. Computer science QA75.5-76.95 Jain Pooja Pachori Ram Bilas Time-Order Representation Based Method for Epoch Detection from Speech Signals |
topic_facet |
speech signal analysis epoch detection pitch frequency estimation voiced detection time-order representation fourier–bessel series expansion Science Q Electronic computers. Computer science QA75.5-76.95 |
description |
Epochs present in the voiced speech are defined as time instants of significant excitation of the vocal tract system during the production of speech. Nonstationary nature of excitation source and vocal tract system makes accurate identification of epochs a difficult task. Most of the existing methods for epoch detection require prior knowledge of voiced regions and a rough estimation of pitch frequency. In this paper, we propose a novel method that relies on time-order representation (TOR) based on short-time Fourier–Bessel (FB) series expansion which can be employed on entire speech signal to detect epochs without any prior information. The proposed method automatically detects voiced regions in the speech signal by computing the marginal energy density with respect to time in the low frequency range (LFR) from the energy distribution in the time-frequency plane. An estimate of pitch frequency for each detected voiced region is then obtained by computing the marginal energy density with respect to frequency in the LFR from the energy distribution in the time-frequency plane. Epochs are located for each detected voiced region as peaks in the derivative of the low pass filtered (LPF) signal corresponding to falling edges of peak negative cycles in the LPF signal synthesized from TOR coefficients corresponding to LFR. Experimental results obtained by the proposed method on speech signals taken from the CMU-Arctic database are found to be promising. The proposed method detects epochs with high accuracy and reliability. |
format |
Article in Journal/Newspaper |
author |
Jain Pooja Pachori Ram Bilas |
author_facet |
Jain Pooja Pachori Ram Bilas |
author_sort |
Jain Pooja |
title |
Time-Order Representation Based Method for Epoch Detection from Speech Signals |
title_short |
Time-Order Representation Based Method for Epoch Detection from Speech Signals |
title_full |
Time-Order Representation Based Method for Epoch Detection from Speech Signals |
title_fullStr |
Time-Order Representation Based Method for Epoch Detection from Speech Signals |
title_full_unstemmed |
Time-Order Representation Based Method for Epoch Detection from Speech Signals |
title_sort |
time-order representation based method for epoch detection from speech signals |
publisher |
De Gruyter |
publishDate |
2012 |
url |
https://doi.org/10.1515/jisys-2012-0003 https://doaj.org/article/77b1e5e6cce94890a292f10d9d927d61 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
Journal of Intelligent Systems, Vol 21, Iss 1, Pp 79-95 (2012) |
op_relation |
https://doi.org/10.1515/jisys-2012-0003 https://doaj.org/toc/0334-1860 https://doaj.org/toc/2191-026X 0334-1860 2191-026X doi:10.1515/jisys-2012-0003 https://doaj.org/article/77b1e5e6cce94890a292f10d9d927d61 |
op_doi |
https://doi.org/10.1515/jisys-2012-0003 |
container_title |
Journal of Intelligent Systems |
container_volume |
21 |
container_issue |
1 |
_version_ |
1766341866396057600 |