{"id":"https://openalex.org/W3015312544","doi":"https://doi.org/10.1109/icassp40776.2020.9053266","title":"Improving Noise Robust Automatic Speech Recognition with Single-Channel Time-Domain Enhancement Network","display_name":"Improving Noise Robust Automatic Speech Recognition with Single-Channel Time-Domain Enhancement Network","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015312544","doi":"https://doi.org/10.1109/icassp40776.2020.9053266","mag":"3015312544"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"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":true,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, 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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, 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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"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":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069398831"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":9.5467,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.9885451,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7009","last_page":"7013"},"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":0.9994999766349792,"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":0.9991000294685364,"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":0.8153287172317505},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.7461752891540527},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7053297162055969},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6402851343154907},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.6018929481506348},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5829404592514038},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5779069662094116},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5489481091499329},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4683000147342682},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4680202901363373},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4467660188674927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4386696517467499},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.42995309829711914},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4151139557361603},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4138905107975006},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3230953514575958},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11564743518829346},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10750004649162292},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10477149486541748},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0603545606136322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153287172317505},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.7461752891540527},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7053297162055969},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6402851343154907},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.6018929481506348},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5829404592514038},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5779069662094116},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5489481091499329},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4680202901363373},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4467660188674927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4386696517467499},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.42995309829711914},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4151139557361603},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4138905107975006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3230953514575958},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11564743518829346},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10750004649162292},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10477149486541748},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0603545606136322},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/icassp40776.2020.9053266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1968939597","https://openalex.org/W2069681747","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2559260703","https://openalex.org/W2640112133","https://openalex.org/W2678916739","https://openalex.org/W2734774145","https://openalex.org/W2792764867","https://openalex.org/W2889258820","https://openalex.org/W2889373351","https://openalex.org/W2892365986","https://openalex.org/W2905649134","https://openalex.org/W2916979304","https://openalex.org/W2937998856","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2962892438","https://openalex.org/W2963045393","https://openalex.org/W2963103134","https://openalex.org/W2963266252","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963828919","https://openalex.org/W2964121744","https://openalex.org/W2972412503","https://openalex.org/W2991015288","https://openalex.org/W3099330747","https://openalex.org/W6631190155","https://openalex.org/W6730321509","https://openalex.org/W6735429107","https://openalex.org/W6735593169","https://openalex.org/W6749825310","https://openalex.org/W6754743415","https://openalex.org/W6757668070"],"related_works":["https://openalex.org/W4287867034","https://openalex.org/W3108403339","https://openalex.org/W2022538999","https://openalex.org/W2162712524","https://openalex.org/W1955763106","https://openalex.org/W2142924612","https://openalex.org/W2002243964","https://openalex.org/W3090086172","https://openalex.org/W3171883019","https://openalex.org/W3005783148"],"abstract_inverted_index":{"With":[0],"the":[1,63,79,124,129,133,152],"advent":[2],"of":[3,22,67,128,132],"deep":[4],"learning,":[5],"research":[6,55,156],"on":[7,46,56,123],"noise-robust":[8],"automatic":[9],"speech":[10,30],"recognition":[11],"(ASR)":[12],"has":[13,52,74],"progressed":[14],"rapidly.":[15],"However,":[16,72],"ASR":[17,43,107,121,147],"performance":[18,39,68,82],"in":[19,62,157],"noisy":[20],"conditions":[21],"single-channel":[23,29,100,130,141],"systems":[24],"remains":[25],"unsatisfactory.":[26],"Indeed,":[27],"most":[28],"enhancement":[31,81],"(SE)":[32],"methods":[33,60],"(denoising)":[34],"have":[35],"brought":[36],"only":[37],"limited":[38],"gains":[40],"over":[41,118],"state-of-the-art":[42],"back-end":[44,122],"trained":[45],"multi-condition":[47],"training":[48],"data.":[49],"Recently,":[50],"there":[51],"been":[53,76],"much":[54],"neural":[57],"network-based":[58],"SE":[59],"working":[61],"time-domain":[64,86,101],"showing":[65],"levels":[66],"never":[69],"attained":[70],"before.":[71],"it":[73],"not":[75],"established":[77],"whether":[78],"high":[80],"achieved":[83],"by":[84],"such":[85],"approaches":[87],"could":[88],"be":[89],"translated":[90],"into":[91],"ASR.":[92],"In":[93],"this":[94],"paper,":[95],"we":[96],"show":[97],"that":[98,140,158],"a":[99,119],"denoising":[102],"approach":[103],"can":[104,144],"significantly":[105],"improve":[106,146],"performance,":[108,148],"providing":[109],"more":[110,155],"than":[111],"30":[112],"%":[113],"relative":[114],"word":[115],"error":[116],"reduction":[117,143],"strong":[120],"real":[125],"evaluation":[126],"data":[127],"track":[131],"CHiME-4":[134],"dataset.":[135],"These":[136],"positive":[137],"results":[138],"demonstrate":[139],"noise":[142],"still":[145],"which":[149],"should":[150],"open":[151],"door":[153],"to":[154],"direction.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}