{"id":"https://openalex.org/W2077541282","doi":"https://doi.org/10.1109/icassp.2014.6854681","title":"Single-channel mixed speech recognition using deep neural networks","display_name":"Single-channel mixed speech recognition using deep neural networks","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2077541282","doi":"https://doi.org/10.1109/icassp.2014.6854681","mag":"2077541282"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5106404246"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":5.17053228,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.96651962,"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":"5632","last_page":"5636"},"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":0.9998999834060669,"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":0.9995999932289124,"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":0.7750124931335449},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7665460109710693},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7583214044570923},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6782761812210083},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6075137853622437},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5506722331047058},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.4970455467700958},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4918673038482666},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4799345135688782},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43993979692459106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42288443446159363},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24719294905662537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750124931335449},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7665460109710693},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7583214044570923},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6782761812210083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6075137853622437},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5506722331047058},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4970455467700958},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4918673038482666},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4799345135688782},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43993979692459106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42288443446159363},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24719294905662537},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"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":21,"referenced_works":["https://openalex.org/W80444264","https://openalex.org/W185399533","https://openalex.org/W1528056001","https://openalex.org/W1788719964","https://openalex.org/W1993882792","https://openalex.org/W2013598660","https://openalex.org/W2015143272","https://openalex.org/W2019034297","https://openalex.org/W2060822897","https://openalex.org/W2062164080","https://openalex.org/W2072184010","https://openalex.org/W2096480681","https://openalex.org/W2116879786","https://openalex.org/W2136439176","https://openalex.org/W2147768505","https://openalex.org/W2149648698","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2964138484","https://openalex.org/W3146812978","https://openalex.org/W4251421713"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W4253186488","https://openalex.org/W2044344400","https://openalex.org/W1996938127","https://openalex.org/W4379116102","https://openalex.org/W3210882018","https://openalex.org/W2970990331","https://openalex.org/W3207178610","https://openalex.org/W3211782752","https://openalex.org/W4309864825"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,27],"study":[4],"the":[5,35,44,57,62,72,81,103,107],"problem":[6],"of":[7,83,90,98],"single-channel":[8],"mixed":[9,24],"speech":[10,25,64],"recognition":[11,67],"using":[12],"deep":[13],"neural":[14],"networks":[15],"(DNNs).":[16],"Using":[17],"a":[18,50,84],"multi-style":[19],"training":[20,31],"strategy":[21],"on":[22,61],"artificially":[23],"data,":[26],"investigate":[28],"several":[29],"different":[30],"setups":[32],"that":[33,71],"enable":[34],"DNN":[36],"to":[37,39,54,80],"generalize":[38],"corresponding":[40],"similar":[41],"patterns":[42],"in":[43],"test":[45],"data.":[46],"We":[47],"also":[48],"introduce":[49],"WFST-based":[51],"two-talker":[52],"decoder":[53],"work":[55],"with":[56,115],"trained":[58],"DNNs.":[59],"Experiments":[60],"2006":[63],"separation":[65],"and":[66,118],"challenge":[68],"task":[69],"demonstrate":[70],"proposed":[73,92],"DNN-based":[74],"system":[75,111],"has":[76],"remarkable":[77],"noise":[78],"robustness":[79],"interference":[82],"competing":[85],"speaker.":[86],"The":[87],"best":[88],"setup":[89],"our":[91],"systems":[93],"achieves":[94],"an":[95],"overall":[96],"WER":[97],"19.7%":[99],"which":[100],"improves":[101],"upon":[102],"results":[104],"obtained":[105],"by":[106,112],"state-of-the-art":[108],"IBM":[109],"superhuman":[110],"1.9%":[113],"absolute,":[114],"fewer":[116],"assumptions":[117],"lower":[119],"computational":[120],"complexity.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}