{"id":"https://openalex.org/W2889698889","doi":"https://doi.org/10.1109/icassp.2018.8461969","title":"Utterance-Wise Recurrent Dropout and Iterative Speaker Adaptation for Robust Monaural Speech Recognition","display_name":"Utterance-Wise Recurrent Dropout and Iterative Speaker Adaptation for Robust Monaural Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2889698889","doi":"https://doi.org/10.1109/icassp.2018.8461969","mag":"2889698889"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peidong Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"4814","last_page":"4818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/monaural","display_name":"Monaural","score":0.9562101364135742},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8055822849273682},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.80422443151474},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5802488923072815},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5338590741157532},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4769660234451294},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47479763627052307},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4376460611820221},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.43382567167282104},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4211590886116028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38786807656288147},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3846796154975891},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16551339626312256},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10200726985931396},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.059615910053253174}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9562101364135742},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8055822849273682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80422443151474},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5802488923072815},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5338590741157532},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4769660234451294},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47479763627052307},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4376460611820221},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.43382567167282104},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4211590886116028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38786807656288147},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3846796154975891},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16551339626312256},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10200726985931396},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.059615910053253174},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322947","display_name":"Sichuan University of Science and Engineering","ror":"https://ror.org/053fzma23"},{"id":"https://openalex.org/F4320324816","display_name":"Universit\u00e4t Paderborn","ror":"https://ror.org/058kzsd48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1524333225","https://openalex.org/W1600744878","https://openalex.org/W1904365287","https://openalex.org/W1992475611","https://openalex.org/W2002342963","https://openalex.org/W2035576074","https://openalex.org/W2079623482","https://openalex.org/W2160306971","https://openalex.org/W2212703438","https://openalex.org/W2239847623","https://openalex.org/W2242685705","https://openalex.org/W2292443655","https://openalex.org/W2296167893","https://openalex.org/W2406264770","https://openalex.org/W2641129314","https://openalex.org/W2747135936","https://openalex.org/W2966212213","https://openalex.org/W3125118953","https://openalex.org/W4297797397","https://openalex.org/W4301083097","https://openalex.org/W6603403951","https://openalex.org/W6631362777","https://openalex.org/W6636934684","https://openalex.org/W6688167117","https://openalex.org/W6766475400"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2944394647","https://openalex.org/W1543248128"],"abstract_inverted_index":{"This":[0],"study":[1,14],"addresses":[2],"monaural":[3,19,56,83],"(single-microphone)":[4],"automatic":[5],"speech":[6,57],"recognition":[7,58],"(ASR)":[8],"in":[9],"adverse":[10],"acoustic":[11],"conditions.":[12],"Our":[13],"builds":[15],"on":[16,54],"a":[17,25,37,67],"state-of-the-art":[18],"robust":[20],"ASR":[21,84],"method":[22,41],"that":[23],"uses":[24],"wide":[26],"residual":[27],"network":[28],"with":[29],"bidirectional":[30],"long":[31],"short-term":[32],"memory":[33],"(BLSTM).":[34],"We":[35],"propose":[36],"novel":[38],"utterance-wise":[39],"dropout":[40],"for":[42],"training":[43],"LSTM":[44],"networks":[45],"and":[46],"an":[47],"iterative":[48],"speaker":[49],"adaptation":[50],"technique.":[51],"When":[52],"evaluated":[53],"the":[55,61,75,80],"task":[59],"of":[60,72],"CHiME-4":[62],"corpus,":[63],"our":[64],"model":[65],"yields":[66],"word":[68],"error":[69],"rate":[70],"(WER)":[71],"8.28%":[73],"using":[74],"baseline":[76],"language":[77],"model,":[78],"outperforming":[79],"previous":[81],"best":[82],"by":[85],"16.19%":[86],"relatively.":[87]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}