{"id":"https://openalex.org/W2126002878","doi":"https://doi.org/10.1109/icassp.2014.6853592","title":"Context dependent state tying for speech recognition using deep neural network acoustic models","display_name":"Context dependent state tying for speech recognition using deep neural network acoustic models","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2126002878","doi":"https://doi.org/10.1109/icassp.2014.6853592","mag":"2126002878"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"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":"Michiel Bacchiani","raw_affiliation_strings":["Google Inc., New York, NY","Google Inc., New York, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York, NY","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050133412","display_name":"David Rybach","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":false,"raw_author_name":"David Rybach","raw_affiliation_strings":["Google Inc., New York, NY","Google Inc., New York, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York, NY","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049614700"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":5.9199,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96267713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"234"},"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":0.9997000098228455,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/tying","display_name":"Tying","score":0.7581981420516968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7493667006492615},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.705569863319397},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7053315043449402},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6504650712013245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6436231136322021},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5663052797317505},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5411798357963562},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5172632336616516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4925301969051361},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4421064853668213},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44022294878959656},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.43027687072753906},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3283344507217407},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24521860480308533}],"concepts":[{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.7581981420516968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7493667006492615},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.705569863319397},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7053315043449402},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6504650712013245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6436231136322021},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5663052797317505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5411798357963562},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5172632336616516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4925301969051361},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4421064853668213},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44022294878959656},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.43027687072753906},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3283344507217407},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24521860480308533},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":2,"locations":[{"id":"doi:10.1109/icassp.2014.6853592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.81","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.81","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/media/research.google.com/en/us/pubs/archive/42652.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1487724677","https://openalex.org/W1987238397","https://openalex.org/W2035424729","https://openalex.org/W2046932483","https://openalex.org/W2076794394","https://openalex.org/W2080209778","https://openalex.org/W2091902552","https://openalex.org/W2105099419","https://openalex.org/W2131342762","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2168231600","https://openalex.org/W2184045248","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2400718301","https://openalex.org/W2403195671","https://openalex.org/W6629045631","https://openalex.org/W6679429981","https://openalex.org/W6684859321","https://openalex.org/W6697318756"],"related_works":["https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2122233706","https://openalex.org/W2888189389","https://openalex.org/W3164030209","https://openalex.org/W642007152","https://openalex.org/W2890297197","https://openalex.org/W2105439218","https://openalex.org/W4377824862","https://openalex.org/W2131711534"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"algorithm":[4,44,64],"to":[5,75],"design":[6],"a":[7,11,25,31,38,71,78],"tied-state":[8,80],"inventory":[9],"for":[10,18,70,77],"context":[12,72],"dependent,":[13],"neural":[14,54],"network-based":[15],"acoustic":[16],"model":[17,40],"speech":[19],"recognition.":[20],"Rather":[21],"than":[22],"relying":[23],"on":[24,30,48],"GMM/HMM":[26],"system":[27,74],"that":[28],"operates":[29],"different":[32,39],"feature":[33],"space":[34],"and":[35],"is":[36],"of":[37,52,61],"family,":[41],"the":[42,49,53,59,62,66],"proposed":[43,63],"optimizes":[45],"state":[46],"tying":[47],"activation":[50],"vectors":[51],"network":[55],"directly.":[56],"Experiments":[57],"show":[58],"viability":[60],"reducing":[65],"WER":[67],"from":[68],"36.3%":[69],"independent":[73],"16.0%":[76],"15000":[79],"system.":[81]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}