Automatic talker activity labeling for co-channel talker interference suppression

A speaker activity detector is described. It takes cochannel speech as input and labeling intervals of the input as target-only, jammer-only, or two-speaker (target and jammer). The algorithms applied are borrowed primarily from speaker recognition, thereby allowing one to use speaker-dependent test...

Full description

Saved in:
Bibliographic Details
Main Authors: Zissman, M.A., Weinstein, C.J., Braida, L.D.
Format: Conference Proceeding
Language:English
Subjects:
Detectors
Interference suppression
Jamming
Labeling
Performance analysis
Speaker recognition
Speech
Testing
Vector quantization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 816 vol.2
container_issue
container_start_page 813
container_title
container_volume
creator Zissman, M.A.
Weinstein, C.J.
Braida, L.D.
description A speaker activity detector is described. It takes cochannel speech as input and labeling intervals of the input as target-only, jammer-only, or two-speaker (target and jammer). The algorithms applied are borrowed primarily from speaker recognition, thereby allowing one to use speaker-dependent test-utterance-independent information in a front-end for cochannel talker interference suppression. Parameters studied include classifier choice (vector quantization vs. Gaussian), training method (unsupervised vs. supervised), test utterance segmentation (uniform vs. adaptive), and training and testing target-to-jammer ratios. Using analysis interval lengths of 100 ms, performance reached 80% correct detection.< >
doi_str_mv 10.1109/ICASSP.1990.115950
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_115950</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>115950</ieee_id><sourcerecordid>115950</sourcerecordid><originalsourceid>FETCH-ieee_primary_1159503</originalsourceid><addsrcrecordid>eNp9jr0KwjAYRYMoWH9ewCkv0JpUa5uxFEU3pQ5uEsNXjaZJSVKhby-irk4XzjnDRWhGSUQpYfNdkZflPqKMvUHCEtJDQbxIWUgZOfVRQJOYhCu6ZEM0cu5OCMnSZRagQ956U3MvBfZcPcBiLrx8St9hxS-gpL7iylgsTChuXGtQv05qD7YCC1oAdm3TWHBOGj1Bg4orB9PvjtFssz4W21ACwLmxsua2O39OLv7KF210QTg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Automatic talker activity labeling for co-channel talker interference suppression</title><source>IEEE Xplore All Conference Series</source><creator>Zissman, M.A. ; Weinstein, C.J. ; Braida, L.D.</creator><creatorcontrib>Zissman, M.A. ; Weinstein, C.J. ; Braida, L.D.</creatorcontrib><description>A speaker activity detector is described. It takes cochannel speech as input and labeling intervals of the input as target-only, jammer-only, or two-speaker (target and jammer). The algorithms applied are borrowed primarily from speaker recognition, thereby allowing one to use speaker-dependent test-utterance-independent information in a front-end for cochannel talker interference suppression. Parameters studied include classifier choice (vector quantization vs. Gaussian), training method (unsupervised vs. supervised), test utterance segmentation (uniform vs. adaptive), and training and testing target-to-jammer ratios. Using analysis interval lengths of 100 ms, performance reached 80% correct detection.&lt; &gt;</description><identifier>ISSN: 1520-6149</identifier><identifier>EISSN: 2379-190X</identifier><identifier>DOI: 10.1109/ICASSP.1990.115950</identifier><language>eng</language><publisher>IEEE</publisher><subject>Detectors ; Interference suppression ; Jamming ; Labeling ; Performance analysis ; Speaker recognition ; Speech ; Testing ; Vector quantization</subject><ispartof>International Conference on Acoustics, Speech, and Signal Processing, 1990, p.813-816 vol.2</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/115950$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,4050,4051,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/115950$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zissman, M.A.</creatorcontrib><creatorcontrib>Weinstein, C.J.</creatorcontrib><creatorcontrib>Braida, L.D.</creatorcontrib><title>Automatic talker activity labeling for co-channel talker interference suppression</title><title>International Conference on Acoustics, Speech, and Signal Processing</title><addtitle>ICASSP</addtitle><description>A speaker activity detector is described. It takes cochannel speech as input and labeling intervals of the input as target-only, jammer-only, or two-speaker (target and jammer). The algorithms applied are borrowed primarily from speaker recognition, thereby allowing one to use speaker-dependent test-utterance-independent information in a front-end for cochannel talker interference suppression. Parameters studied include classifier choice (vector quantization vs. Gaussian), training method (unsupervised vs. supervised), test utterance segmentation (uniform vs. adaptive), and training and testing target-to-jammer ratios. Using analysis interval lengths of 100 ms, performance reached 80% correct detection.&lt; &gt;</description><subject>Detectors</subject><subject>Interference suppression</subject><subject>Jamming</subject><subject>Labeling</subject><subject>Performance analysis</subject><subject>Speaker recognition</subject><subject>Speech</subject><subject>Testing</subject><subject>Vector quantization</subject><issn>1520-6149</issn><issn>2379-190X</issn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1990</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNp9jr0KwjAYRYMoWH9ewCkv0JpUa5uxFEU3pQ5uEsNXjaZJSVKhby-irk4XzjnDRWhGSUQpYfNdkZflPqKMvUHCEtJDQbxIWUgZOfVRQJOYhCu6ZEM0cu5OCMnSZRagQ956U3MvBfZcPcBiLrx8St9hxS-gpL7iylgsTChuXGtQv05qD7YCC1oAdm3TWHBOGj1Bg4orB9PvjtFssz4W21ACwLmxsua2O39OLv7KF210QTg</recordid><startdate>1990</startdate><enddate>1990</enddate><creator>Zissman, M.A.</creator><creator>Weinstein, C.J.</creator><creator>Braida, L.D.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1990</creationdate><title>Automatic talker activity labeling for co-channel talker interference suppression</title><author>Zissman, M.A. ; Weinstein, C.J. ; Braida, L.D.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_1159503</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1990</creationdate><topic>Detectors</topic><topic>Interference suppression</topic><topic>Jamming</topic><topic>Labeling</topic><topic>Performance analysis</topic><topic>Speaker recognition</topic><topic>Speech</topic><topic>Testing</topic><topic>Vector quantization</topic><toplevel>online_resources</toplevel><creatorcontrib>Zissman, M.A.</creatorcontrib><creatorcontrib>Weinstein, C.J.</creatorcontrib><creatorcontrib>Braida, L.D.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zissman, M.A.</au><au>Weinstein, C.J.</au><au>Braida, L.D.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Automatic talker activity labeling for co-channel talker interference suppression</atitle><btitle>International Conference on Acoustics, Speech, and Signal Processing</btitle><stitle>ICASSP</stitle><date>1990</date><risdate>1990</risdate><spage>813</spage><epage>816 vol.2</epage><pages>813-816 vol.2</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><abstract>A speaker activity detector is described. It takes cochannel speech as input and labeling intervals of the input as target-only, jammer-only, or two-speaker (target and jammer). The algorithms applied are borrowed primarily from speaker recognition, thereby allowing one to use speaker-dependent test-utterance-independent information in a front-end for cochannel talker interference suppression. Parameters studied include classifier choice (vector quantization vs. Gaussian), training method (unsupervised vs. supervised), test utterance segmentation (uniform vs. adaptive), and training and testing target-to-jammer ratios. Using analysis interval lengths of 100 ms, performance reached 80% correct detection.&lt; &gt;</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.1990.115950</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1520-6149
ispartof International Conference on Acoustics, Speech, and Signal Processing, 1990, p.813-816 vol.2
issn 1520-6149
2379-190X
language eng
recordid cdi_ieee_primary_115950
source IEEE Xplore All Conference Series
subjects Detectors
Interference suppression
Jamming
Labeling
Performance analysis
Speaker recognition
Speech
Testing
Vector quantization
title Automatic talker activity labeling for co-channel talker interference suppression
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T11%3A28%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Automatic%20talker%20activity%20labeling%20for%20co-channel%20talker%20interference%20suppression&rft.btitle=International%20Conference%20on%20Acoustics,%20Speech,%20and%20Signal%20Processing&rft.au=Zissman,%20M.A.&rft.date=1990&rft.spage=813&rft.epage=816%20vol.2&rft.pages=813-816%20vol.2&rft.issn=1520-6149&rft.eissn=2379-190X&rft_id=info:doi/10.1109/ICASSP.1990.115950&rft_dat=%3Cieee_CHZPO%3E115950%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-ieee_primary_1159503%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=115950&rfr_iscdi=true