{"id":"https://openalex.org/W3171794711","doi":"https://doi.org/10.21437/interspeech.2021-2253","title":"Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition","display_name":"Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3171794711","doi":"https://doi.org/10.21437/interspeech.2021-2253","mag":"3171794711"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2253","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.00949.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049917170","display_name":"Hiroshi Sat\u014d","orcid":"https://orcid.org/0000-0002-5899-1340"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT (Japan), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT (Japan), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT (Japan), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034382743","display_name":"Naoyuki Kamo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Kamo","raw_affiliation_strings":["NTT (Japan), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1149","last_page":"1153"},"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":0.9998000264167786,"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":0.9986000061035156,"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/speech-recognition","display_name":"Speech recognition","score":0.790590763092041},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.757112979888916},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6866075396537781},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6509425640106201},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6077948212623596},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5715512633323669},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.5324906706809998},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4987521171569824},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.43249496817588806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33329063653945923},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.31324660778045654},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09710440039634705}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.790590763092041},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757112979888916},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6866075396537781},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6509425640106201},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6077948212623596},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5715512633323669},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.5324906706809998},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4987521171569824},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.43249496817588806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33329063653945923},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.31324660778045654},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09710440039634705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2021-2253","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"mag:3171794711","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.00949.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.00949","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.00949","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"mag:3171794711","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.00949.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1755563775","https://openalex.org/W1992475611","https://openalex.org/W2101045344","https://openalex.org/W2117678320","https://openalex.org/W2160815625","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2407080277","https://openalex.org/W2589857635","https://openalex.org/W2891833136","https://openalex.org/W2936774411","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2962892438","https://openalex.org/W2963266252","https://openalex.org/W2963843276","https://openalex.org/W2964121744","https://openalex.org/W2972362771","https://openalex.org/W2972389417","https://openalex.org/W2972412503","https://openalex.org/W2972474532","https://openalex.org/W3015636705","https://openalex.org/W3034729383","https://openalex.org/W3096090308"],"related_works":["https://openalex.org/W3198667862","https://openalex.org/W2047919706","https://openalex.org/W1575946971","https://openalex.org/W2896532092","https://openalex.org/W2747006289","https://openalex.org/W2067181967","https://openalex.org/W2526714731","https://openalex.org/W2924429671","https://openalex.org/W2399989146","https://openalex.org/W2418631473","https://openalex.org/W642885585","https://openalex.org/W2768416973","https://openalex.org/W3111611403","https://openalex.org/W2784507976","https://openalex.org/W2145525565","https://openalex.org/W112875839","https://openalex.org/W2528751956","https://openalex.org/W2962959469","https://openalex.org/W2548398025","https://openalex.org/W2049585404"],"abstract_inverted_index":{"Although":[0],"recent":[1],"advances":[2],"in":[3,92],"deep":[4,42],"learning":[5],"technology":[6],"improved":[7],"automatic":[8],"speech":[9,17,45,98,124,135,145,170],"recognition":[10,191],"(ASR),":[11],"it":[12,19,64,104],"remains":[13],"difficult":[14],"to":[15,34,36,90,114,122,198],"recognize":[16],"when":[18,95,193],"overlaps":[20],"other":[21],"people's":[22],"voices.":[23],"Speech":[24],"separation":[25],"or":[26],"extraction":[27],"is":[28,65,105],"often":[29,77],"used":[30],"as":[31,51],"a":[32,52,100,162,185],"front-end":[33],"ASR":[35,60,91,129,148],"handle":[37],"such":[38,184],"overlapping":[39,97,154],"speech.":[40,155],"However,":[41],"neural":[43],"network-based":[44],"enhancement":[46,146],"can":[47,189],"generate":[48],"`processing":[49],"artifacts'":[50],"side":[53],"effect":[54],"of":[55],"the":[56,83,116,173],"enhancement,":[57],"which":[58],"degrades":[59,147],"performance.":[61],"For":[62],"example,":[63],"well":[66],"known":[67],"that":[68,108,144,183],"single-channel":[69],"noise":[70,74,138],"reduction":[71],"for":[72,153],"non-speech":[73],"(non-overlapping":[75],"speech)":[76],"does":[78],"not":[79],"improve":[80,190],"ASR.":[81,111,199],"Likewise,":[82],"processing":[84,96,194],"artifacts":[85,195],"may":[86],"also":[87],"be":[88],"detrimental":[89,197],"some":[93,150],"conditions":[94,151],"with":[99],"separation/extraction":[101,109],"method,":[102],"although":[103],"usually":[106],"believed":[107],"improves":[110],"In":[112],"order":[113],"answer":[115],"question":[117],"`Do":[118],"we":[119,127,160],"always":[120],"have":[121],"separate/extract":[123],"from":[125],"mixtures?',":[126],"analyze":[128],"performance":[130,192],"on":[131,157,172],"observed":[132,167],"and":[133,139,142,168,177],"enhanced":[134,169],"at":[136],"various":[137],"interference":[140],"conditions,":[141],"show":[143],"under":[149],"even":[152],"Based":[156],"these":[158],"findings,":[159],"propose":[161],"simple":[163,186],"switching":[164,187],"algorithm":[165],"between":[166],"based":[171],"estimated":[174],"signal-to-interference":[175],"ratio":[176],"signal-to-noise":[178],"ratio.":[179],"We":[180],"demonstrated":[181],"experimentally":[182],"mechanism":[188],"are":[196]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}