{"id":"https://openalex.org/W2957895207","doi":"https://doi.org/10.21437/interspeech.2019-2641","title":"Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition","display_name":"Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2957895207","doi":"https://doi.org/10.21437/interspeech.2019-2641","mag":"2957895207"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2641","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.04887","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004052692","display_name":"Khoi-Nguyen C. Mac","orcid":"https://orcid.org/0000-0003-4623-4016"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khoi-Nguyen C. Mac","raw_affiliation_strings":["***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441789","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0003-3605-9373"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"251","last_page":"255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9995999932289124,"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":0.7984015941619873},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.797357976436615},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.7240549325942993},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6289526224136353},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5924428105354309},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5899491310119629},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.4601939022541046},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.41913288831710815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29403164982795715},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.27049678564071655},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08954387903213501},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07781815528869629}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7984015941619873},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.797357976436615},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.7240549325942993},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6289526224136353},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5924428105354309},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5899491310119629},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.4601939022541046},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.41913288831710815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29403164982795715},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27049678564071655},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08954387903213501},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07781815528869629},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2641","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.04887","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.04887","pdf_url":"https://arxiv.org/pdf/1907.04887","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2957895207","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1907.04887","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.04887","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.04887","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.04887","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.04887","pdf_url":"https://arxiv.org/pdf/1907.04887","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2957895207.pdf","grobid_xml":"https://content.openalex.org/works/W2957895207.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W204144752","https://openalex.org/W1997763773","https://openalex.org/W2013598660","https://openalex.org/W2049633694","https://openalex.org/W2099471712","https://openalex.org/W2146423068","https://openalex.org/W2158843472","https://openalex.org/W2171815504","https://openalex.org/W2284177371","https://openalex.org/W2399742709","https://openalex.org/W2550246519","https://openalex.org/W2557113115","https://openalex.org/W2784918340","https://openalex.org/W2904310189","https://openalex.org/W2939878283","https://openalex.org/W2962835968"],"related_works":["https://openalex.org/W2973141395","https://openalex.org/W3008987902","https://openalex.org/W3015837673","https://openalex.org/W2801903454","https://openalex.org/W3149951309","https://openalex.org/W2115914516","https://openalex.org/W2040091543","https://openalex.org/W1753444788","https://openalex.org/W2067256546","https://openalex.org/W2950237361","https://openalex.org/W2923231620","https://openalex.org/W2794974041","https://openalex.org/W3161411401","https://openalex.org/W3016022729","https://openalex.org/W2937829825","https://openalex.org/W2109706882","https://openalex.org/W3172622380","https://openalex.org/W3027119780","https://openalex.org/W3112318417","https://openalex.org/W2136509013"],"abstract_inverted_index":{"In":[0,34],"automatic":[1],"speech":[2,10],"recognition":[3],"(ASR),":[4],"wideband":[5],"(WB)":[6],"and":[7,55,69,76,84],"narrowband":[8],"(NB)":[9],"signals":[11],"with":[12,94],"different":[13],"sampling":[14],"rates":[15],"typically":[16],"use":[17],"separate":[18],"acoustic":[19,24,45,74],"models.":[20],"Therefore":[21],"mixed-bandwidth":[22],"(MB)":[23],"modeling":[25,46,75],"has":[26],"important":[27],"practical":[28],"values":[29],"for":[30,47,72],"ASR":[31,48],"system":[32],"deployment.":[33],"this":[35],"paper,":[36],"we":[37],"extensively":[38],"investigate":[39],"large-scale":[40],"MB":[41,64,73],"deep":[42],"neural":[43],"network":[44],"using":[49,109],"1,150":[50],"hours":[51,57],"of":[52,58,98],"WB":[53,83],"data":[54,111],"2,300":[56],"NB":[59,85],"data.":[60],"We":[61],"study":[62],"various":[63,89],"strategies":[65],"including":[66],"downsampling,":[67],"upsampling":[68],"bandwidth":[70],"extension":[71],"evaluate":[77],"their":[78],"performance":[79],"on":[80,106],"8":[81],"diverse":[82],"test":[86],"sets":[87],"from":[88],"application":[90],"domains.":[91],"To":[92],"deal":[93],"the":[95],"large":[96],"amounts":[97],"training":[99,102],"data,":[100],"distributed":[101],"is":[103],"carried":[104],"out":[105],"multiple":[107],"GPUs":[108],"synchronous":[110],"parallelism.":[112]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}