{"id":"https://openalex.org/W2972757492","doi":"https://doi.org/10.21437/interspeech.2019-2244","title":"Multi-Channel Block-Online Source Extraction Based on Utterance Adaptation","display_name":"Multi-Channel Block-Online Source Extraction Based on Utterance Adaptation","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972757492","doi":"https://doi.org/10.21437/interspeech.2019-2244","mag":"2972757492"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2244","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064609638","display_name":"Juan M. Mart\u00edn-Do\u00f1as","orcid":"https://orcid.org/0000-0003-4874-0166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan M. Mart\u00edn-Do\u00f1as","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021547071","display_name":"Jens Heitkaemper","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jens Heitkaemper","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024291487","display_name":"\u00c1ngel M. G\u00f3mez","orcid":"https://orcid.org/0000-0002-9995-3068"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Angel M. Gomez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078514616","display_name":"Antonio M. Peinado","orcid":"https://orcid.org/0000-0001-8214-6676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio M. Peinado","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6676,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69121675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8242144584655762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6782922148704529},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5542367696762085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5399659872055054},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5270215272903442},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5144577026367188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.499774694442749},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.440116286277771},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4237344264984131},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4176703989505768},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09965798258781433},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08824756741523743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242144584655762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6782922148704529},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5542367696762085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5399659872055054},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5270215272903442},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5144577026367188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.499774694442749},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.440116286277771},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4237344264984131},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4176703989505768},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09965798258781433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08824756741523743},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-2244","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1754457604","https://openalex.org/W2141998673","https://openalex.org/W2221409856","https://openalex.org/W2289480995","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2749510669","https://openalex.org/W2890553422","https://openalex.org/W2891609809","https://openalex.org/W2891833136","https://openalex.org/W2892163332","https://openalex.org/W2900212944","https://openalex.org/W2909607850","https://openalex.org/W2942172990","https://openalex.org/W2950108968","https://openalex.org/W2964058413","https://openalex.org/W2966212213","https://openalex.org/W2970789614"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2095030957","https://openalex.org/W2066827917"],"abstract_inverted_index":{"This":[0],"paper":[1],"deals":[2],"with":[3,9],"multi-channel":[4],"speech":[5],"recognition":[6,167],"in":[7,148,150,161],"scenarios":[8],"multiple":[10],"speakers.":[11,66],"Recently,":[12],"the":[13,76,93,112,120,133,140,151],"spectral":[14,54,83,100],"characteristics":[15],"of":[16,47,114,127,163],"a":[17,30,71,80,115],"target":[18,63,98],"speaker,":[19],"extracted":[20,105],"from":[21,106],"an":[22,107],"adaptation":[23,108],"utterance,":[24],"have":[25],"been":[26],"used":[27],"to":[28,35,58,75],"guide":[29],"neural":[31,49,94],"network":[32],"mask":[33,77,95],"estimator":[34],"focus":[36],"on":[37],"that":[38,130,139,155],"speaker.":[39],"In":[40],"this":[41],"work":[42],"we":[43,68],"present":[44],"two":[45],"variants":[46],"speakeraware":[48],"networks,":[50],"which":[51],"exploit":[52],"both":[53],"and":[55,64,101,154,166],"spatial":[56,72,81,102,142],"information":[57,143],"allow":[59],"better":[60],"discrimination":[61],"between":[62],"interfering":[65],"Thus,":[67],"introduce":[69],"either":[70],"preprocessing":[73],"prior":[74],"estimation":[78],"or":[79],"plus":[82],"speaker":[84],"characterization":[85],"block":[86],"whose":[87],"output":[88],"is":[89,104],"directly":[90],"fed":[91],"into":[92],"estimator.":[96],"The":[97],"speaker\u2019s":[99],"signature":[103],"utterance":[109],"recorded":[110],"at":[111],"beginning":[113],"session.":[116],"We":[117],"further":[118],"adapt":[119],"architecture":[121],"for":[122],"low-latency":[123],"processing":[124],"by":[125],"means":[126],"block-online":[128],"beamforming":[129],"recursively":[131],"updates":[132],"signal":[134],"statistics.":[135],"Experimental":[136],"results":[137],"show":[138],"additional":[141],"clearly":[144],"improves":[145],"source":[146],"extraction,":[147],"particular":[149],"same-gender":[152],"case,":[153],"our":[156],"proposal":[157],"achieves":[158],"state-of-the-art":[159],"performance":[160],"terms":[162],"distortion":[164],"reduction":[165],"accuracy.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}