{"id":"https://openalex.org/W2899829828","doi":"https://doi.org/10.1109/icassp.2019.8683648","title":"Reinforcement Learning Based Speech Enhancement for Robust Speech Recognition","display_name":"Reinforcement Learning Based Speech Enhancement for Robust Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2899829828","doi":"https://doi.org/10.1109/icassp.2019.8683648","mag":"2899829828"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5063025053","display_name":"Yih-Liang Shen","orcid":"https://orcid.org/0000-0003-4789-6695"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yih-Liang Shen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, R.O.C","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002718759","display_name":"Chao-Yuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Yuan Huang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, R.O.C","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073046122","display_name":"Syu\u2010Siang Wang","orcid":"https://orcid.org/0000-0002-2652-5521"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Syu-Siang Wang","raw_affiliation_strings":["Joint Research Center for AI Technology and All Vista Healthcare, MOST, Taipei, R.O.C"],"affiliations":[{"raw_affiliation_string":"Joint Research Center for AI Technology and All Vista Healthcare, MOST, Taipei, R.O.C","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, R.O.C"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, R.O.C","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Joint Research Center for AI Technology and All Vista Healthcare, MOST, Taipei, R.O.C"],"affiliations":[{"raw_affiliation_string":"Joint Research Center for AI Technology and All Vista Healthcare, MOST, Taipei, R.O.C","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088864528","display_name":"Tai-Shih Chi","orcid":"https://orcid.org/0000-0002-0584-8399"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai-Shih Chi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, R.O.C","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063025053"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":3.11942174,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.9241337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6750","last_page":"6754"},"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":0.9983000159263611,"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":0.818657636642456},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7626062631607056},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.718651294708252},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5474697351455688},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5417215824127197},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5341120958328247},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5283297300338745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4729352295398712},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.454422265291214},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37312912940979004},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17944711446762085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08997699618339539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818657636642456},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7626062631607056},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.718651294708252},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5474697351455688},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5417215824127197},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5341120958328247},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5283297300338745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4729352295398712},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.454422265291214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37312912940979004},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17944711446762085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08997699618339539},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1498717522","https://openalex.org/W1524333225","https://openalex.org/W1552314771","https://openalex.org/W1681299129","https://openalex.org/W1975301756","https://openalex.org/W1990005421","https://openalex.org/W2044893557","https://openalex.org/W2098414234","https://openalex.org/W2113307832","https://openalex.org/W2113911479","https://openalex.org/W2134237567","https://openalex.org/W2139053308","https://openalex.org/W2141998673","https://openalex.org/W2143555316","https://openalex.org/W2145339207","https://openalex.org/W2169147844","https://openalex.org/W2296167893","https://openalex.org/W2405774341","https://openalex.org/W2408592723","https://openalex.org/W2408713104","https://openalex.org/W2560747691","https://openalex.org/W2584390378","https://openalex.org/W2696558042","https://openalex.org/W2772297474","https://openalex.org/W2805233667","https://openalex.org/W2888858245","https://openalex.org/W2889500840","https://openalex.org/W2892129657","https://openalex.org/W2962866211","https://openalex.org/W2963211572","https://openalex.org/W2963796169","https://openalex.org/W3103619082","https://openalex.org/W3196059551","https://openalex.org/W4294087448","https://openalex.org/W6631362777","https://openalex.org/W6633117090","https://openalex.org/W6662018355","https://openalex.org/W6674565355","https://openalex.org/W6676931166","https://openalex.org/W6681377254","https://openalex.org/W6713658392","https://openalex.org/W6713729801","https://openalex.org/W6713796627","https://openalex.org/W6746059548"],"related_works":["https://openalex.org/W2374317326","https://openalex.org/W2990005675","https://openalex.org/W2080787847","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2163874654","https://openalex.org/W2401089611"],"abstract_inverted_index":{"Conventional":[0],"deep":[1],"neural":[2],"network":[3],"(DNN)-based":[4],"speech":[5,19,35],"enhancement":[6],"(SE)":[7],"approaches":[8],"aim":[9],"to":[10,43,54,93,100,150],"minimize":[11,44],"the":[12,30,40,45,48,56,61,65,95,102,107,112,118,129,136],"mean":[13],"square":[14],"error":[15,145],"(MSE)":[16],"between":[17],"enhanced":[18],"and":[20,79,85,143,157],"clean":[21],"reference.":[22],"The":[23],"MSE-optimized":[24],"model":[25,104],"may":[26],"not":[27,86],"directly":[28],"improve":[29,135],"performance":[31],"of":[32,67,73],"an":[33,68],"automatic":[34],"recognition":[36,46,49,108],"(ASR)":[37],"system.":[38],"If":[39],"target":[41],"is":[42,82],"error,":[47],"results":[50,126,138],"should":[51],"be":[52],"used":[53],"design":[55],"objective":[57],"function":[58],"for":[59,148],"optimizing":[60],"SE":[62,103,115,131],"model.":[63],"However,":[64],"structure":[66],"ASR":[69,137],"system,":[70],"which":[71],"consists":[72],"multiple":[74],"units,":[75],"such":[76],"as":[77],"acoustic":[78],"language":[80],"models,":[81],"usually":[83],"complex":[84],"differentiable.":[87],"In":[88],"this":[89],"study,":[90],"we":[91],"propose":[92],"adopt":[94],"reinforcement":[96],"learning":[97],"(RL)":[98],"algorithm":[99],"optimize":[101],"based":[105],"on":[106,117],"results.":[109],"We":[110],"evaluated":[111],"proposed":[113,130],"RL-based":[114],"system":[116,132],"Mandarin":[119],"Chinese":[120],"broadcast":[121],"news":[122],"corpus":[123],"(MATBN).":[124],"Experimental":[125],"demonstrate":[127],"that":[128],"can":[133],"effectively":[134],"with":[139],"a":[140],"notable":[141],"12:40%":[142],"19:23%":[144],"rate":[146],"reductions":[147],"signal":[149],"noise":[151],"ratio":[152],"(SNR)":[153],"at":[154],"0":[155],"dB":[156,159],"5":[158],"conditions,":[160],"respectively.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}