{"id":"https://openalex.org/W3008987902","doi":"https://doi.org/10.1109/asru46091.2019.9003760","title":"Mixed Bandwidth Acoustic Modeling Leveraging Knowledge Distillation","display_name":"Mixed Bandwidth Acoustic Modeling Leveraging Knowledge Distillation","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008987902","doi":"https://doi.org/10.1109/asru46091.2019.9003760","mag":"3008987902"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003760","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5102876935","display_name":"Takashi Fukuda","orcid":"https://orcid.org/0000-0002-4601-0955"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takashi Fukuda","raw_affiliation_strings":["IBM Research AI, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"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":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102876935"],"corresponding_institution_ids":["https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67925027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"16","issue":null,"first_page":"509","last_page":"515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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":0.9988999962806702,"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":0.705572247505188},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6862213611602783},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5291063189506531},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.158191978931427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705572247505188},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6862213611602783},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5291063189506531},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.158191978931427},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003760","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W17608502","https://openalex.org/W1517841224","https://openalex.org/W1602122992","https://openalex.org/W1821462560","https://openalex.org/W1984541135","https://openalex.org/W2013598660","https://openalex.org/W2083751884","https://openalex.org/W2108817613","https://openalex.org/W2134797427","https://openalex.org/W2136933783","https://openalex.org/W2173379916","https://openalex.org/W2198724430","https://openalex.org/W2245569228","https://openalex.org/W2400830530","https://openalex.org/W2402040300","https://openalex.org/W2507699225","https://openalex.org/W2508418541","https://openalex.org/W2512865187","https://openalex.org/W2518315489","https://openalex.org/W2633884958","https://openalex.org/W2747909401","https://openalex.org/W2910715461","https://openalex.org/W2911629330","https://openalex.org/W2913178639","https://openalex.org/W2936993002","https://openalex.org/W2937657912","https://openalex.org/W2963217176","https://openalex.org/W2963266252","https://openalex.org/W2963376890","https://openalex.org/W2963726581","https://openalex.org/W2963927463","https://openalex.org/W4293871399","https://openalex.org/W6600728236","https://openalex.org/W6679909955","https://openalex.org/W6680549991","https://openalex.org/W6685316698","https://openalex.org/W6690610466","https://openalex.org/W6697339895","https://openalex.org/W6712847557","https://openalex.org/W6713030564","https://openalex.org/W6759502261"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Training":[0],"of":[1,37,123],"mixed":[2],"bandwidth":[3],"acoustic":[4,85],"models":[5],"have":[6],"recently":[7],"been":[8],"realized":[9],"by":[10,114],"incorporating":[11],"special":[12,116],"Mel":[13,90,117],"filterbanks.":[14,91,118],"To":[15],"fit":[16],"information":[17,109],"into":[18],"every":[19],"filterbank":[20],"bin":[21],"available":[22],"across":[23],"both":[24,128],"narrowband":[25,38,58,129],"and":[26,134],"wideband":[27,135],"data,":[28,52],"these":[29,41,68,99],"filterbanks":[30],"pad":[31],"zeros":[32],"at":[33,110],"high":[34,111],"frequency":[35],"ranges":[36],"data.":[39],"Although":[40],"methods":[42,65],"succeed":[43],"in":[44],"decreasing":[45],"word":[46],"error":[47],"rates":[48],"(WER)":[49],"on":[50,57,83,141],"broadband":[51],"they":[53],"fail":[54],"to":[55,66,105],"improve":[56],"signals.":[59],"In":[60,74],"this":[61],"paper,":[62],"we":[63],"propose":[64],"mitigate":[67],"effects":[69],"with":[70,87],"generalized":[71],"knowledge":[72,97],"distillation.":[73],"our":[75],"method,":[76],"specialized":[77],"teacher":[78,100],"networks":[79,101],"are":[80],"first":[81],"trained":[82],"lossless":[84],"features":[86],"full":[88],"scale":[89],"While":[92],"training":[93],"student":[94],"networks,":[95],"privileged":[96],"from":[98],"is":[102],"then":[103],"used":[104],"compensate":[106],"for":[107,127],"missing":[108],"frequencies":[112],"introduced":[113],"the":[115,121,124,142],"We":[119],"show":[120],"benefit":[122],"proposed":[125],"technique":[126],"(10%":[130],"relative":[131,138],"WER":[132,139],"improvement)":[133,140],"data":[136],"(7.5%":[137],"Aurora":[143],"4":[144],"task":[145],"over":[146],"traditional":[147],"methods.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}