{"id":"https://openalex.org/W3163341049","doi":"https://doi.org/10.1109/icassp39728.2021.9414280","title":"Teacher-Student Learning for Low-Latency Online Speech Enhancement Using Wave-U-Net","display_name":"Teacher-Student Learning for Low-Latency Online Speech Enhancement Using Wave-U-Net","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163341049","doi":"https://doi.org/10.1109/icassp39728.2021.9414280","mag":"3163341049"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5022600606","display_name":"Sotaro Nakaoka","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Sotaro Nakaoka","raw_affiliation_strings":["University of Tsukuba,Japan","University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361230","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-7163-6263"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["University of Tsukuba,Japan","University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051093194","display_name":"Shota Inoue","orcid":"https://orcid.org/0000-0002-8754-0397"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Inoue","raw_affiliation_strings":["University of Tsukuba,Japan","University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["University of Tsukuba,Japan","University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022600606"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":2.7425,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90892495,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"661","last_page":"665"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/latency","display_name":"Latency (audio)","score":0.7943869829177856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622547149658203},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.6356759667396545},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.511534571647644},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.49118611216545105},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48281678557395935},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4644233286380768},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44789278507232666},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.44349074363708496},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4213874340057373},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3958676755428314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30877166986465454},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.17992380261421204},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17013266682624817},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1451111137866974},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10723593831062317}],"concepts":[{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7943869829177856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622547149658203},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.6356759667396545},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.511534571647644},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.49118611216545105},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48281678557395935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4644233286380768},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44789278507232666},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.44349074363708496},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4213874340057373},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3958676755428314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30877166986465454},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.17992380261421204},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17013266682624817},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1451111137866974},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10723593831062317},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W88987024","https://openalex.org/W95152782","https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1821462560","https://openalex.org/W1897240248","https://openalex.org/W2037635165","https://openalex.org/W2044893557","https://openalex.org/W2067295501","https://openalex.org/W2070126272","https://openalex.org/W2127851351","https://openalex.org/W2291877678","https://openalex.org/W2889134433","https://openalex.org/W2889442120","https://openalex.org/W2894785362","https://openalex.org/W2902132730","https://openalex.org/W2911629330","https://openalex.org/W2936252403","https://openalex.org/W2937484199","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963189033","https://openalex.org/W2963341071","https://openalex.org/W2963452667","https://openalex.org/W2963927463","https://openalex.org/W2964203871","https://openalex.org/W3097945073","https://openalex.org/W4253928870","https://openalex.org/W4289242435","https://openalex.org/W4293871399","https://openalex.org/W6603838645","https://openalex.org/W6633117090","https://openalex.org/W6638523607","https://openalex.org/W6662018355","https://openalex.org/W6678799340","https://openalex.org/W6697339895","https://openalex.org/W6735429107","https://openalex.org/W6748163181","https://openalex.org/W6751512325","https://openalex.org/W6756251360"],"related_works":["https://openalex.org/W1630865680","https://openalex.org/W4214692512","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W4308600690"],"abstract_inverted_index":{"In":[0,79],"this":[1,80,108],"paper,":[2,81],"we":[3,82,110],"propose":[4,117],"a":[5,32,97,142,167],"low-latency":[6,99,162],"online":[7,112],"extension":[8],"of":[9,100,114,120,171],"wave-U-net":[10,60,84,115],"for":[11],"single-channel":[12],"speech":[13,48],"enhancement,":[14],"which":[15,39],"utilizes":[16],"teacher-student":[17,121],"learning":[18,122],"to":[19,85,123],"reduce":[20],"the":[21,26,52,57,68,73,118,125,130,138,154],"system":[22,139],"latency":[23],"while":[24],"keeping":[25],"enhancement":[27,49,53],"performance":[28,42,126],"high.":[29],"Wave-U-net":[30],"is":[31,54,76,105,144],"recently":[33],"proposed":[34,155],"end-to-end":[35],"source":[36],"separation":[37,46],"method,":[38],"achieved":[40],"remarkable":[41],"in":[43,56,132,141,159],"singing":[44],"voice":[45],"and":[47,66,92,116,163],"tasks.":[50],"Since":[51],"performed":[55],"time":[58],"domain,":[59],"can":[61],"efficiently":[62],"model":[63,156],"phase":[64],"information":[65],"address":[67],"domain":[69,75],"transformation":[70],"limitation,":[71],"where":[72,96],"time-frequency":[74],"normally":[77],"adopted.":[78],"apply":[83],"face-to-face":[86],"applications":[87],"such":[88,136],"as":[89],"hearing":[90],"aids":[91],"in-car":[93],"communication":[94],"systems,":[95],"strictly":[98],"less":[101,145],"than":[102,146],"10":[103,147],"ms":[104],"required.":[106],"To":[107],"end,":[109],"investigate":[111],"versions":[113],"use":[119],"prevent":[124],"degradation":[127],"caused":[128],"by":[129],"reduction":[131],"input":[133],"segment":[134],"length":[135],"that":[137,153],"delay":[140],"CPU":[143],"ms.":[148],"The":[149],"experimental":[150],"results":[151],"revealed":[152],"could":[157],"perform":[158],"real-time":[160],"with":[161],"high":[164],"performance,":[165],"achieving":[166],"signal-to-distortion":[168],"ratio":[169],"improvement":[170],"about":[172],"8.73":[173],"dB.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}