{"id":"https://openalex.org/W3194687854","doi":"https://doi.org/10.21437/interspeech.2021-921","title":"Investigation of Practical Aspects of Single Channel Speech Separation for ASR","display_name":"Investigation of Practical Aspects of Single Channel Speech Separation for ASR","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3194687854","doi":"https://doi.org/10.21437/interspeech.2021-921","mag":"3194687854"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-921","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-921","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":"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/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jian Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106557560","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-8483-1578"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079533447","display_name":"Sanyuan Chen","orcid":"https://orcid.org/0000-0002-3082-6052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanyuan Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324098","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-1680-8253"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101674460"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2189,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79188641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3066","last_page":"3070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7202812433242798},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6688500642776489},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6034317016601562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5167214274406433},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3297162353992462},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14049601554870605},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08245843648910522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7202812433242798},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6688500642776489},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6034317016601562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5167214274406433},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3297162353992462},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14049601554870605},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08245843648910522}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-921","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-921","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W4292513318"],"abstract_inverted_index":{"Speech":[0],"separation":[1,40,71],"has":[2],"been":[3],"successfully":[4],"applied":[5],"as":[6,32],"a":[7,38,49,67,76,83,111,125],"frontend":[8],"processing":[9],"module":[10],"of":[11,66,130],"conversation":[12],"transcription":[13],"systems":[14],"thanks":[15],"to":[16,19,26,62,104],"its":[17,24],"ability":[18],"handle":[20],"overlapped":[21],"speech":[22,34,39,45,70,100],"and":[23,132,154],"flexibility":[25],"combine":[27],"with":[28,136,142],"downstream":[29],"tasks":[30],"such":[31],"automatic":[33],"recognition":[35,101],"(ASR).":[36],"However,":[37],"model":[41,107,117],"often":[42],"introduces":[43],"target":[44],"distortion,":[46],"resulting":[47],"in":[48],"sub-optimum":[50],"word":[51],"error":[52],"rate":[53],"(WER).":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,74,109,123],"describe":[59],"our":[60],"efforts":[61],"improve":[63],"the":[64,106,143,148],"performance":[65],"single":[68],"channel":[69],"system.":[72],"Specifically,":[73],"investigate":[75],"two-stage":[77],"training":[78],"scheme":[79],"that":[80],"firstly":[81],"applies":[82],"feature":[84],"level":[85],"optimization":[86,94],"criterion":[87,95],"for":[88,116,151],"pretraining,":[89],"followed":[90],"by":[91],"an":[92,97],"ASR-oriented":[93],"using":[96,134],"end-to-end":[98],"(E2E)":[99],"model.":[102],"Meanwhile,":[103],"keep":[105],"light-weight,":[108],"introduce":[110],"modified":[112],"teacher-student":[113],"learning":[114],"technique":[115],"compression.":[118],"By":[119],"combining":[120],"those":[121],"approaches,":[122],"achieve":[124],"absolute":[126],"average":[127],"WER":[128],"improvement":[129],"2.70%":[131],"0.77%":[133],"models":[135],"less":[137],"than":[138],"10M":[139],"parameters":[140],"compared":[141],"previous":[144],"state-of-the-art":[145],"results":[146],"on":[147],"LibriCSS":[149],"dataset":[150],"utterance-wise":[152],"evaluation":[153],"continuous":[155],"evaluation,":[156],"respectively":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}