{"id":"https://openalex.org/W2937170468","doi":"https://doi.org/10.1109/icassp.2019.8682556","title":"Acoustic Modeling for Overlapping Speech Recognition: Jhu Chime-5 Challenge System","display_name":"Acoustic Modeling for Overlapping Speech Recognition: Jhu Chime-5 Challenge System","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937170468","doi":"https://doi.org/10.1109/icassp.2019.8682556","mag":"2937170468"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682556","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":"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/A5028956985","display_name":"Vimal Manohar","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vimal Manohar","raw_affiliation_strings":["Human Language Technology Center Of Excellence, Johns Hopkins University, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center Of Excellence, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065795147","display_name":"Szu-Jui Chen","orcid":"https://orcid.org/0000-0002-6406-9280"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Szu-Jui Chen","raw_affiliation_strings":["Center for Language and Speech Processing"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100601882","display_name":"Zhiqi Wang","orcid":"https://orcid.org/0000-0003-4536-6252"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Zhiqi Wang","raw_affiliation_strings":["Center for Language and Speech Processing"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["Center for Language and Speech Processing"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Center for Language and Speech Processing"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Human Language Technology Center Of Excellence, Johns Hopkins University, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center Of Excellence, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5028956985"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":3.3171,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92991285,"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":"6665","last_page":"6669"},"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":0.9998000264167786,"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":0.7701641321182251},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7036471366882324},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6233049631118774},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5768043398857117},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5503923892974854},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5116958618164062},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49837803840637207},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.460834801197052},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4524286687374115},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.42340797185897827},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32924026250839233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3255555033683777},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06896594166755676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701641321182251},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7036471366882324},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6233049631118774},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5768043398857117},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5503923892974854},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5116958618164062},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49837803840637207},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.460834801197052},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4524286687374115},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.42340797185897827},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32924026250839233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3255555033683777},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06896594166755676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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.2019.8682556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682556","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":0.5099999904632568,"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":35,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1836465849","https://openalex.org/W1989314204","https://openalex.org/W2095705004","https://openalex.org/W2101045344","https://openalex.org/W2117678320","https://openalex.org/W2127141656","https://openalex.org/W2150769028","https://openalex.org/W2164240571","https://openalex.org/W2164502538","https://openalex.org/W2219249508","https://openalex.org/W2288817436","https://openalex.org/W2289912446","https://openalex.org/W2293634267","https://openalex.org/W2510616059","https://openalex.org/W2514741789","https://openalex.org/W2559260703","https://openalex.org/W2696967604","https://openalex.org/W2747135936","https://openalex.org/W2782451907","https://openalex.org/W2884797218","https://openalex.org/W2888867175","https://openalex.org/W2900440209","https://openalex.org/W2916979304","https://openalex.org/W2949117887","https://openalex.org/W2963197115","https://openalex.org/W2964286182","https://openalex.org/W6631362777","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6688816777","https://openalex.org/W6696934422","https://openalex.org/W6743201256","https://openalex.org/W6747836893","https://openalex.org/W6766380642"],"related_works":["https://openalex.org/W876328409","https://openalex.org/W3081187864","https://openalex.org/W151018310","https://openalex.org/W4380605396","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2584084702","https://openalex.org/W2784059283","https://openalex.org/W3012383599","https://openalex.org/W4385611764"],"abstract_inverted_index":{"This":[0],"paper":[1],"summarizes":[2],"our":[3,49],"acoustic":[4],"modeling":[5],"efforts":[6],"in":[7],"the":[8,16,66,76],"Johns":[9],"Hopkins":[10],"University":[11],"speech":[12,24,39],"recognition":[13],"system":[14],"for":[15],"CHiME-5":[17,92],"challenge":[18],"to":[19],"recognize":[20],"highly-overlapped":[21],"dinner":[22],"party":[23],"recorded":[25],"by":[26],"multiple":[27],"microphone":[28],"arrays.":[29],"We":[30,56],"explore":[31],"data":[32],"augmentation":[33],"approaches,":[34],"neural":[35],"network":[36],"architectures,":[37],"front-end":[38],"dereverberation,":[40],"beamforming":[41],"and":[42,52,81],"robust":[43],"i-vector":[44],"extraction":[45],"with":[46,86],"comparisons":[47],"of":[48,63,79],"in-house":[50],"implementations":[51],"publicly":[53],"available":[54],"tools.":[55],"finally":[57],"achieved":[58],"a":[59,71],"word":[60],"error":[61],"rate":[62],"69.4%":[64],"on":[65],"development":[67],"set,":[68],"which":[69],"is":[70],"11.7%":[72],"absolute":[73],"improvement":[74],"over":[75],"previous":[77],"baseline":[78,85],"81.1%,":[80],"release":[82],"this":[83],"improved":[84],"refined":[87],"techniques/tools":[88],"as":[89],"an":[90],"advanced":[91],"recipe.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}