The SRI system for the NIST OpenSAD 2015 speech activity detection evaluation

In this paper, we present the SRI system submission to the NIST OpenSAD 2015 speech activity detection (SAD) evaluation. We present results on three different development databases that we created from the provided data. We present system-development results for feature normalization; for feature fu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Graciarena, M., Ferrer, L., Mitra, V., Morgan N., Georgiou P., Narayanan S., Metze F., Amazon Alexa; Apple; eBay; et al.; Google; Microsoft
Formato:	CONF
Materias:	Channel degradation Noise robustness Speech activity detection Calibration Speech Speech communication Speech processing Testing Adaptive calibration Bottleneck features Channel bottlenecks Channel degradations Decision threshold Feature normalization Speech activity detections Speech recognition
Acceso en línea:	http://hdl.handle.net/20.500.12110/paper_2308457X_v08-12-September-2016_n_p3673_Graciarena
Aporte de:	Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires

id	todo:paper_2308457X_v08-12-September-2016_n_p3673_Graciarena
record_format	dspace
spelling	todo:paper_2308457X_v08-12-September-2016_n_p3673_Graciarena2023-10-03T16:40:51Z The SRI system for the NIST OpenSAD 2015 speech activity detection evaluation Graciarena, M. Ferrer, L. Mitra, V. Morgan N. Georgiou P. Morgan N. Narayanan S. Metze F. Amazon Alexa; Apple; eBay; et al.; Google; Microsoft Channel degradation Noise robustness Speech activity detection Calibration Speech Speech communication Speech processing Testing Adaptive calibration Bottleneck features Channel bottlenecks Channel degradations Decision threshold Feature normalization Noise robustness Speech activity detections Speech recognition In this paper, we present the SRI system submission to the NIST OpenSAD 2015 speech activity detection (SAD) evaluation. We present results on three different development databases that we created from the provided data. We present system-development results for feature normalization; for feature fusion with acoustic, voicing, and channel bottleneck features; and finally for SAD bottleneck-feature fusion. We present a novel technique called test adaptive calibration, which is designed to improve decision-threshold selection for each test waveform. We present unsupervised test adaptation of the fusion component and describe its tight synergy to the test adaptive calibration component. Finally, we present results on the evaluation test data and show how the proposed techniques lead to significant gains on channels unseen during training. Copyright © 2016 ISCA. CONF info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_2308457X_v08-12-September-2016_n_p3673_Graciarena
institution	Universidad de Buenos Aires
institution_str	I-28
repository_str	R-134
collection	Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic	Channel degradation Noise robustness Speech activity detection Calibration Speech Speech communication Speech processing Testing Adaptive calibration Bottleneck features Channel bottlenecks Channel degradations Decision threshold Feature normalization Noise robustness Speech activity detections Speech recognition
spellingShingle	Channel degradation Noise robustness Speech activity detection Calibration Speech Speech communication Speech processing Testing Adaptive calibration Bottleneck features Channel bottlenecks Channel degradations Decision threshold Feature normalization Noise robustness Speech activity detections Speech recognition Graciarena, M. Ferrer, L. Mitra, V. Morgan N. Georgiou P. Morgan N. Narayanan S. Metze F. Amazon Alexa; Apple; eBay; et al.; Google; Microsoft The SRI system for the NIST OpenSAD 2015 speech activity detection evaluation
topic_facet	Channel degradation Noise robustness Speech activity detection Calibration Speech Speech communication Speech processing Testing Adaptive calibration Bottleneck features Channel bottlenecks Channel degradations Decision threshold Feature normalization Noise robustness Speech activity detections Speech recognition
description	In this paper, we present the SRI system submission to the NIST OpenSAD 2015 speech activity detection (SAD) evaluation. We present results on three different development databases that we created from the provided data. We present system-development results for feature normalization; for feature fusion with acoustic, voicing, and channel bottleneck features; and finally for SAD bottleneck-feature fusion. We present a novel technique called test adaptive calibration, which is designed to improve decision-threshold selection for each test waveform. We present unsupervised test adaptation of the fusion component and describe its tight synergy to the test adaptive calibration component. Finally, we present results on the evaluation test data and show how the proposed techniques lead to significant gains on channels unseen during training. Copyright © 2016 ISCA.
format	CONF
author	Graciarena, M. Ferrer, L. Mitra, V. Morgan N. Georgiou P. Morgan N. Narayanan S. Metze F. Amazon Alexa; Apple; eBay; et al.; Google; Microsoft
author_facet	Graciarena, M. Ferrer, L. Mitra, V. Morgan N. Georgiou P. Morgan N. Narayanan S. Metze F. Amazon Alexa; Apple; eBay; et al.; Google; Microsoft
author_sort	Graciarena, M.
title	The SRI system for the NIST OpenSAD 2015 speech activity detection evaluation
title_short	The SRI system for the NIST OpenSAD 2015 speech activity detection evaluation
title_full	The SRI system for the NIST OpenSAD 2015 speech activity detection evaluation
title_fullStr	The SRI system for the NIST OpenSAD 2015 speech activity detection evaluation
title_full_unstemmed	The SRI system for the NIST OpenSAD 2015 speech activity detection evaluation
title_sort	sri system for the nist opensad 2015 speech activity detection evaluation
url	http://hdl.handle.net/20.500.12110/paper_2308457X_v08-12-September-2016_n_p3673_Graciarena
work_keys_str_mv	AT graciarenam thesrisystemforthenistopensad2015speechactivitydetectionevaluation AT ferrerl thesrisystemforthenistopensad2015speechactivitydetectionevaluation AT mitrav thesrisystemforthenistopensad2015speechactivitydetectionevaluation AT morgann thesrisystemforthenistopensad2015speechactivitydetectionevaluation AT georgioup thesrisystemforthenistopensad2015speechactivitydetectionevaluation AT morgann thesrisystemforthenistopensad2015speechactivitydetectionevaluation AT narayanans thesrisystemforthenistopensad2015speechactivitydetectionevaluation AT metzef thesrisystemforthenistopensad2015speechactivitydetectionevaluation AT amazonalexaappleebayetalgooglemicrosoft thesrisystemforthenistopensad2015speechactivitydetectionevaluation AT graciarenam srisystemforthenistopensad2015speechactivitydetectionevaluation AT ferrerl srisystemforthenistopensad2015speechactivitydetectionevaluation AT mitrav srisystemforthenistopensad2015speechactivitydetectionevaluation AT morgann srisystemforthenistopensad2015speechactivitydetectionevaluation AT georgioup srisystemforthenistopensad2015speechactivitydetectionevaluation AT morgann srisystemforthenistopensad2015speechactivitydetectionevaluation AT narayanans srisystemforthenistopensad2015speechactivitydetectionevaluation AT metzef srisystemforthenistopensad2015speechactivitydetectionevaluation AT amazonalexaappleebayetalgooglemicrosoft srisystemforthenistopensad2015speechactivitydetectionevaluation
_version_	1807319052635340800

The SRI system for the NIST OpenSAD 2015 speech activity detection evaluation

Ejemplares similares