Robust Speech Features based on synchrony spectrum determination using PLLs
In this work we propose to include synchrony effects, known to exist in the auditory system, to represent speech signal information in a robust way. The system decomposes the signal in a number of simpler signals, and utilizes a bank of Phase Locked Loops (PLLs) to obtain information of the frequenc...
Autores principales: | , , |
---|---|
Formato: | Objeto de conferencia |
Lenguaje: | Inglés |
Publicado: |
2010
|
Materias: | |
Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/152593 http://39jaiio.sadio.org.ar/sites/default/files/39jaiio-asai-08.pdf |
Aporte de: |
id |
I19-R120-10915-152593 |
---|---|
record_format |
dspace |
spelling |
I19-R120-10915-1525932023-05-08T20:03:56Z http://sedici.unlp.edu.ar/handle/10915/152593 http://39jaiio.sadio.org.ar/sites/default/files/39jaiio-asai-08.pdf issn:1850-2784 Robust Speech Features based on synchrony spectrum determination using PLLs Pelle, Patricia Alejandra Franco, Horacio Estienne, Claudio 2010 2010 2023-05-08T18:01:21Z en Ciencias Informáticas speech features robustness PLL noise auditory system In this work we propose to include synchrony effects, known to exist in the auditory system, to represent speech signal information in a robust way. The system decomposes the signal in a number of simpler signals, and utilizes a bank of Phase Locked Loops (PLLs) to obtain information of the frequencies present at each time. This information is interpolated in order to obtain a spectral-like representation based in synchrony effects, measured by the PLLs. Noisy speech recognition experiments are performed using this synchrony-based spectrum, which is transformed into a small set of coefficients by using a similar transformation as the one utilized for the Mel cepstrum features. We show their recognition performance compared to Mel cepstrum features obtained from the standard power spectrum. Some recognition improvements are obtained for the case of vocalic sounds for this approach, especially in the case of severe noise conditions. Sociedad Argentina de Informática e Investigación Operativa Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 82-91 |
institution |
Universidad Nacional de La Plata |
institution_str |
I-19 |
repository_str |
R-120 |
collection |
SEDICI (UNLP) |
language |
Inglés |
topic |
Ciencias Informáticas speech features robustness PLL noise auditory system |
spellingShingle |
Ciencias Informáticas speech features robustness PLL noise auditory system Pelle, Patricia Alejandra Franco, Horacio Estienne, Claudio Robust Speech Features based on synchrony spectrum determination using PLLs |
topic_facet |
Ciencias Informáticas speech features robustness PLL noise auditory system |
description |
In this work we propose to include synchrony effects, known to exist in the auditory system, to represent speech signal information in a robust way. The system decomposes the signal in a number of simpler signals, and utilizes a bank of Phase Locked Loops (PLLs) to obtain information of the frequencies present at each time. This information is interpolated in order to obtain a spectral-like representation based in synchrony effects, measured by the PLLs. Noisy speech recognition experiments are performed using this synchrony-based spectrum, which is transformed into a small set of coefficients by using a similar transformation as the one utilized for the Mel cepstrum features. We show their recognition performance compared to Mel cepstrum features obtained from the standard power spectrum. Some recognition improvements are obtained for the case of vocalic sounds for this approach, especially in the case of severe noise conditions. |
format |
Objeto de conferencia Objeto de conferencia |
author |
Pelle, Patricia Alejandra Franco, Horacio Estienne, Claudio |
author_facet |
Pelle, Patricia Alejandra Franco, Horacio Estienne, Claudio |
author_sort |
Pelle, Patricia Alejandra |
title |
Robust Speech Features based on synchrony spectrum determination using PLLs |
title_short |
Robust Speech Features based on synchrony spectrum determination using PLLs |
title_full |
Robust Speech Features based on synchrony spectrum determination using PLLs |
title_fullStr |
Robust Speech Features based on synchrony spectrum determination using PLLs |
title_full_unstemmed |
Robust Speech Features based on synchrony spectrum determination using PLLs |
title_sort |
robust speech features based on synchrony spectrum determination using plls |
publishDate |
2010 |
url |
http://sedici.unlp.edu.ar/handle/10915/152593 http://39jaiio.sadio.org.ar/sites/default/files/39jaiio-asai-08.pdf |
work_keys_str_mv |
AT pellepatriciaalejandra robustspeechfeaturesbasedonsynchronyspectrumdeterminationusingplls AT francohoracio robustspeechfeaturesbasedonsynchronyspectrumdeterminationusingplls AT estienneclaudio robustspeechfeaturesbasedonsynchronyspectrumdeterminationusingplls |
_version_ |
1765660134231506944 |