{"id":"https://openalex.org/W2400335852","doi":"https://doi.org/10.1109/icassp.2016.7472714","title":"Sequence training of multi-task acoustic models using meta-state labels","display_name":"Sequence training of multi-task acoustic models using meta-state labels","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2400335852","doi":"https://doi.org/10.1109/icassp.2016.7472714","mag":"2400335852"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":["Google Inc., New York"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005881531"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.12750752,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90773767,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5425","last_page":"5429"},"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/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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7281903028488159},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6955630779266357},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6797610521316528},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6516703367233276},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6385864019393921},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6315525770187378},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.5804628133773804},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5518923997879028},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.479576051235199},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4590846598148346},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.45329636335372925},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.44534602761268616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4079180955886841},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36438608169555664},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19539383053779602},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08154293894767761},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08059123158454895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281903028488159},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6955630779266357},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6797610521316528},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6516703367233276},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6385864019393921},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6315525770187378},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.5804628133773804},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5518923997879028},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.479576051235199},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4590846598148346},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.45329636335372925},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.44534602761268616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4079180955886841},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36438608169555664},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19539383053779602},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08154293894767761},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08059123158454895},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1545083717","https://openalex.org/W1600744878","https://openalex.org/W1606350000","https://openalex.org/W1904457459","https://openalex.org/W2035846950","https://openalex.org/W2094035326","https://openalex.org/W2105852393","https://openalex.org/W2137630452","https://openalex.org/W2155117693","https://openalex.org/W2160237783","https://openalex.org/W2160815625","https://openalex.org/W2292439652","https://openalex.org/W2295983515","https://openalex.org/W2397569915","https://openalex.org/W2398836258","https://openalex.org/W2400651116","https://openalex.org/W2407320368","https://openalex.org/W6636469245","https://openalex.org/W6639829665","https://openalex.org/W6697215464","https://openalex.org/W6712759826","https://openalex.org/W6713047518","https://openalex.org/W6713403589"],"related_works":["https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W1989270116","https://openalex.org/W2030109976","https://openalex.org/W2369260257","https://openalex.org/W2389120450","https://openalex.org/W55249799"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,49,92],"describe":[4],"a":[5,36,64,89,101,116],"multi-task":[6],"learning":[7,32],"approach":[8,33],"for":[9,56],"acoustic":[10],"modeling":[11],"where":[12],"the":[13,29,44,75,78,96,105],"multiple":[14,97],"output":[15,40,46,54,98],"layers":[16,41,55,99],"are":[17,113],"used":[18],"to":[19,51,94],"predict":[20],"context-dependent":[21],"(CD)":[22],"states":[23,72],"from":[24],"different":[25,79],"state":[26,107],"inventories.":[27],"Unlike":[28],"traditional":[30],"multitask":[31],"which":[34],"defines":[35],"primary":[37],"and":[38,73],"secondary":[39,45],"but":[42],"discards":[43],"after":[47],"training,":[48],"propose":[50,93],"use":[52],"all":[53],"recognition.":[57],"This":[58],"can":[59],"be":[60],"achieved":[61],"by":[62],"designing":[63],"decoding":[65],"network":[66],"operating":[67],"on":[68,115,122],"tuples":[69,108],"of":[70,77],"CD":[71,106],"combining":[74],"scores":[76],"outputs":[80],"during":[81],"search.":[82],"To":[83],"support":[84],"training":[85],"such":[86],"models":[87],"using":[88],"sequence-based":[90],"criterion,":[91],"replace":[95],"with":[100],"single":[102],"layer":[103],"encoding":[104],"as":[109],"\"meta-states\".":[110],"Experimental":[111],"results":[112],"given":[114],"large":[117],"Voice":[118],"Search":[119],"task":[120],"evaluated":[121],"children's":[123],"speech.":[124]},"counts_by_year":[{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}