{"id":"https://openalex.org/W2939878283","doi":"https://doi.org/10.1109/icassp.2019.8682760","title":"Cyclegan Bandwidth Extension Acoustic Modeling for Automatic Speech Recognition","display_name":"Cyclegan Bandwidth Extension Acoustic Modeling for Automatic Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939878283","doi":"https://doi.org/10.1109/icassp.2019.8682760","mag":"2939878283"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682760","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/A5049318367","display_name":"David Haws","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Haws","raw_affiliation_strings":["IBM T. J. Watson Research Center, IBM Research AI, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, IBM Research AI, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM T. J. Watson Research Center, IBM Research AI, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, IBM Research AI, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049318367"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":1.161,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.78433779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6780","last_page":"6784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8056263327598572},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7314966917037964},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.7054817080497742},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6839190125465393},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6222988367080688},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.49748948216438293},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49671250581741333},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4268644452095032},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.42522409558296204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4137769341468811},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38608217239379883},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.23556780815124512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8056263327598572},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7314966917037964},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.7054817080497742},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6839190125465393},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6222988367080688},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.49748948216438293},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49671250581741333},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4268644452095032},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.42522409558296204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4137769341468811},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38608217239379883},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.23556780815124512},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682760","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W204144752","https://openalex.org/W1997763773","https://openalex.org/W2020683423","https://openalex.org/W2146423068","https://openalex.org/W2171815504","https://openalex.org/W2284177371","https://openalex.org/W2784918340","https://openalex.org/W2787133659","https://openalex.org/W2795050058","https://openalex.org/W2796010067","https://openalex.org/W2962719052","https://openalex.org/W2962793481","https://openalex.org/W2962879692","https://openalex.org/W2963057973","https://openalex.org/W2964069186","https://openalex.org/W2972817136","https://openalex.org/W4254041323","https://openalex.org/W4295521014","https://openalex.org/W6649844427","https://openalex.org/W6735913928","https://openalex.org/W6748056815","https://openalex.org/W6765398037","https://openalex.org/W6779669310"],"related_works":["https://openalex.org/W3031135612","https://openalex.org/W3012110132","https://openalex.org/W3198995983","https://openalex.org/W2162743322","https://openalex.org/W2150814427","https://openalex.org/W3093686966","https://openalex.org/W3097573669","https://openalex.org/W1504449689","https://openalex.org/W2345067732","https://openalex.org/W3168285598","https://openalex.org/W2969430620","https://openalex.org/W3164223074","https://openalex.org/W2572023240","https://openalex.org/W37288447","https://openalex.org/W3199713199","https://openalex.org/W2895807593","https://openalex.org/W2591810467","https://openalex.org/W2797187289","https://openalex.org/W1486143877","https://openalex.org/W2221901388"],"abstract_inverted_index":{"Although":[0],"narrowband":[1,125],"(NB)":[2],"and":[3,65,76,106],"wideband":[4],"(WB)":[5],"speech":[6,25],"data":[7],"primarily":[8],"differ":[9],"in":[10,39,110],"sampling":[11],"rate,":[12],"these":[13],"two":[14],"common":[15],"input":[16],"sources":[17],"are":[18],"difficult":[19],"to":[20,51,58,81,94,113,121,127],"simultaneously":[21],"model":[22,117],"for":[23],"automatic":[24],"recognition":[26],"(ASR).":[27],"Meanwhile,":[28],"cycle":[29],"consistent":[30],"generative":[31],"adversarial":[32],"networks":[33],"(CycleGANs)":[34],"have":[35],"been":[36],"shown":[37],"value":[38],"a":[40,67,114],"number":[41],"of":[42,61,69],"acoustic":[43],"tasks":[44],"such":[45],"as":[46],"mapping":[47],"between":[48],"domains":[49],"due":[50],"their":[52],"powerful":[53],"generators.":[54],"We":[55],"apply":[56],"Cycle-GAN":[57],"the":[59,95],"task":[60],"bandwidth":[62],"extension":[63],"(BWE)":[64],"test":[66],"variety":[68],"architectures.":[70],"The":[71],"CycleGANs":[72],"produce":[73],"encouraging":[74],"losses":[75],"reconstructed":[77],"spectrograms.":[78],"In":[79],"order":[80],"further":[82],"reduce":[83],"word":[84],"error":[85],"rates":[86],"(WER)":[87],"we":[88,107],"add":[89],"an":[90],"additional":[91],"discriminative":[92],"loss":[93],"CycleGAN":[96],"BWE":[97,116],"architecture.":[98],"This":[99],"more":[100],"closely":[101],"matches":[102],"our":[103],"ASR":[104],"goal":[105],"show":[108],"gains":[109],"WER":[111],"compared":[112],"standard":[115],"discriminatively":[118],"trained":[119],"only":[120],"map":[122],"from":[123],"upsampled":[124],"(UNB)":[126],"WB":[128],"data.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}