{"id":"https://openalex.org/W2289731793","doi":"https://doi.org/10.1109/asru.2015.7404833","title":"The MERL/SRI system for the 3RD CHiME challenge using beamforming, robust feature extraction, and advanced speech recognition","display_name":"The MERL/SRI system for the 3RD CHiME challenge using beamforming, robust feature extraction, and advanced speech recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2289731793","doi":"https://doi.org/10.1109/asru.2015.7404833","mag":"2289731793"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Columbia University, New York, NY, USA","Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091201226","display_name":"Vikramjit Mitra","orcid":"https://orcid.org/0000-0002-2721-3976"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"475","last_page":"481"},"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":0.9997000098228455,"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":0.9986000061035156,"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":0.8151895403862},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7630793452262878},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5926387310028076},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5743763446807861},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5721964240074158},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5659032464027405},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5336146354675293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4768489599227905},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4652783274650574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46155428886413574},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.4608101546764374},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.4413266181945801},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4408942461013794},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.43249616026878357},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4203128218650818},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41471874713897705},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.28634560108184814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151895403862},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7630793452262878},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5926387310028076},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5743763446807861},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5721964240074158},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5659032464027405},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5336146354675293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4768489599227905},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4652783274650574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46155428886413574},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.4608101546764374},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.4413266181945801},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4408942461013794},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.43249616026878357},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4203128218650818},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41471874713897705},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.28634560108184814},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2015.7404833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.sabanciuniv.edu:28867","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402254","display_name":"Sabanci University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134235054","host_organization_name":"Sabanc\u0131 \u00dcniversitesi","host_organization_lineage":["https://openalex.org/I134235054"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W173561343","https://openalex.org/W179875071","https://openalex.org/W1482149378","https://openalex.org/W1524333225","https://openalex.org/W1934041838","https://openalex.org/W1981730446","https://openalex.org/W1989314204","https://openalex.org/W2002342963","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2070707809","https://openalex.org/W2097927681","https://openalex.org/W2101045344","https://openalex.org/W2108072369","https://openalex.org/W2114863372","https://openalex.org/W2141411743","https://openalex.org/W2148613904","https://openalex.org/W2168729028","https://openalex.org/W2289394825","https://openalex.org/W2395321025","https://openalex.org/W2950186769","https://openalex.org/W6607114211","https://openalex.org/W6631362777","https://openalex.org/W6668037159","https://openalex.org/W6712234020"],"related_works":["https://openalex.org/W2767070583","https://openalex.org/W2784052451","https://openalex.org/W1494724239","https://openalex.org/W2401089611","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2348931051","https://openalex.org/W4290708361"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"the":[3,8,28,31,36,94,151,156,163,179,188],"MERL/SRI":[4],"system":[5,19],"designed":[6],"for":[7,101,178],"3rd":[9],"CHiME":[10],"speech":[11,33,104],"separation":[12],"and":[13,115,134],"recognition":[14,105,123],"challenge":[15],"(CHiME-3).":[16],"Our":[17,128],"proposed":[18,86],"takes":[20],"advantage":[21],"of":[22,42,159,190],"recurrent":[23],"neural":[24,109],"networks":[25],"(RNNs)":[26],"throughout":[27],"model":[29,142],"from":[30,170],"front":[32],"enhancement":[34,70],"to":[35,46,50,75,120,146,187],"language":[37,118],"modeling.":[38],"Two":[39],"different":[40,171],"types":[41],"beamforming":[43],"are":[44,91,99],"used":[45,74,92,100,145],"combine":[47],"multi-microphone":[48],"signals":[49],"obtain":[51],"a":[52,63,183],"single":[53],"higher":[54],"quality":[55],"signal.":[56,96],"Beamformed":[57],"signal":[58],"is":[59,73,144],"further":[60],"processed":[61],"by":[62],"single-channel":[64],"bi-directional":[65],"long":[66],"short-term":[67],"memory":[68],"(LSTM)":[69],"network":[71,110],"which":[72],"extract":[76],"stacked":[77],"mel-frequency":[78],"cepstral":[79],"coefficients":[80],"(MFCC)":[81],"features.":[82],"In":[83],"addition,":[84],"two":[85],"noise-robust":[87],"feature":[88],"extraction":[89],"methods":[90],"with":[93,107],"beamformed":[95],"The":[97],"features":[98],"decoding":[102],"in":[103,125],"systems":[106,173],"deep":[108],"(DNN)":[111],"based":[112],"acoustic":[113],"models":[114,119],"large-scale":[116],"RNN":[117],"achieve":[121],"high":[122],"accuracy":[124],"noisy":[126],"environments.":[127],"training":[129],"methodology":[130],"includes":[131],"data":[132],"augmentation":[133],"speaker":[135],"adaptive":[136],"training,":[137],"whereas":[138],"at":[139],"test":[140,181],"time":[141],"combination":[143],"improve":[147],"generalization.":[148],"Results":[149],"on":[150],"CHiME-3":[152],"benchmark":[153],"show":[154],"that":[155],"full":[157],"cadre":[158],"techniques":[160],"substantially":[161],"reduced":[162],"word":[164],"error":[165],"rate":[166],"(WER).":[167],"Combining":[168],"hypotheses":[169],"robust-feature":[172],"ultimately":[174],"achieved":[175],"9.10%":[176],"WER":[177],"real":[180],"data,":[182],"72.4%":[184],"reduction":[185],"relative":[186],"baseline":[189],"32.99%":[191],"WER.":[192]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}