{"id":"https://openalex.org/W2973138437","doi":"https://doi.org/10.21437/interspeech.2019-3056","title":"Acoustic-to-Phrase Models for Speech Recognition","display_name":"Acoustic-to-Phrase Models for Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2973138437","doi":"https://doi.org/10.21437/interspeech.2019-3056","mag":"2973138437"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3056","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3056","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":"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/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034136587"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1201,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83984122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2240","last_page":"2244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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":0.7990531921386719},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7080872058868408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6468790173530579},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6390713453292847},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5981322526931763},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5770934224128723},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5763764381408691},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5675846338272095},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5646166801452637},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.529850959777832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5183349847793579},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5089023113250732},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5042575597763062},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47277405858039856},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.45325782895088196},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.199683278799057},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18414315581321716},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08291119337081909}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990531921386719},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7080872058868408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6468790173530579},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6390713453292847},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5981322526931763},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5770934224128723},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5763764381408691},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5675846338272095},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5646166801452637},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.529850959777832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5183349847793579},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5089023113250732},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5042575597763062},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47277405858039856},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.45325782895088196},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.199683278799057},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18414315581321716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08291119337081909},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-3056","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3056","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1904365287","https://openalex.org/W1924770834","https://openalex.org/W2005708641","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2128084896","https://openalex.org/W2131774270","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2513383847","https://openalex.org/W2545177271","https://openalex.org/W2577366047","https://openalex.org/W2597757402","https://openalex.org/W2746192915","https://openalex.org/W2899771611","https://openalex.org/W2952021518","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2963414781","https://openalex.org/W2963483399","https://openalex.org/W2963920996"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W2114358883"],"abstract_inverted_index":{"Directly":[0,65],"emitting":[1,78],"words":[2,38,54,80,133,174],"and":[3,24,55,117,134],"sub-words":[4],"from":[5],"speech":[6],"spectrogram":[7],"has":[8,153],"been":[9,122],"shown":[10,32],"to":[11,58,124,146,172],"produce":[12],"good":[13],"results":[14],"using":[15],"end-to-end":[16],"(E2E)":[17],"trained":[18,123],"models.":[19],"Connectionist":[20],"Temporal":[21],"Classification":[22],"(CTC)":[23],"Sequence-to-Sequence":[25],"attention":[26],"(Seq2Seq)":[28],"models":[29,87,119],"have":[30,121],"both":[31],"better":[33,71],"success":[34],"when":[35],"directly":[36,57,145],"targeting":[37],"or":[39],"sub-words.":[40],"In":[41],"this":[42],"work,":[43],"we":[44,98],"ask":[45],"the":[46,182],"question:":[47],"Can":[48],"an":[49,139],"E2E":[50,140],"model":[51,141,162],"go":[52],"beyond":[53],"transcribe":[56,144],"phrases":[59,68,168],"(i.e.,":[60],"a":[61,100,103,112,126,159,178],"group":[62],"of":[63,128],"words)?":[64],"modeling":[66,73,157],"frequent":[67],"might":[69,82],"be":[70],"than":[72],"its":[74],"constituent":[75],"words.":[76],"Also,":[77],"multiple":[79],"together":[81],"speed":[83],"up":[84,171],"inference":[85],"in":[86,155,181],"like":[88,163],"Seq2Seq":[89,118,164],"where":[90],"decoding":[91],"is":[92],"inherently":[93],"sequential.":[94],"To":[95],"answer":[96],"this,":[97],"undertake":[99],"study":[101],"on":[102],"3400-hour":[104],"Microsoft":[105],"Cortana":[106],"voice":[107],"assistant":[108],"task.":[109],"We":[110,136,148],"present":[111],"side-by-side":[113],"comparison":[114],"for":[115],"CTC":[116,152],"that":[120,138,150,169],"target":[125,167],"variety":[127],"tokens":[129],"including":[130],"letters,":[131],"sub-words,":[132],"phrases.":[135,147],"show":[137],"can":[142,165],"indeed":[143],"see":[149],"while":[151],"difficulty":[154],"accurately":[156],"phrases,":[158],"more":[160],"powerful":[161],"effortlessly":[166],"are":[170],"4":[173],"long,":[175],"with":[176],"only":[177],"reasonable":[179],"degradation":[180],"final":[183],"word":[184],"error":[185],"rate.":[186]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}