{"id":"https://openalex.org/W2404856031","doi":"https://doi.org/10.1109/icassp.2016.7472710","title":"Flat start training of CD-CTC-SMBR LSTM RNN acoustic models","display_name":"Flat start training of CD-CTC-SMBR LSTM RNN acoustic models","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2404856031","doi":"https://doi.org/10.1109/icassp.2016.7472710","mag":"2404856031"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472710","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/A5111514705","display_name":"Kanishka Rao","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":"Kanishka Rao","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079708487","display_name":"Andrew Senior","orcid":"https://orcid.org/0000-0002-2401-5691"},"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":"Andrew Senior","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108537573","display_name":"Ha\u015fim Sak","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":"Hasim Sak","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111514705"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":6.4271,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96648933,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"5405","last_page":"5409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.984000027179718,"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":0.5591226816177368},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3802133798599243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5591226816177368},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3802133798599243}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472710","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1489125746","https://openalex.org/W1525636403","https://openalex.org/W1533416326","https://openalex.org/W1600744878","https://openalex.org/W1966147466","https://openalex.org/W1986184096","https://openalex.org/W2105099419","https://openalex.org/W2127141656","https://openalex.org/W2137644731","https://openalex.org/W2158069733","https://openalex.org/W2165712214","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2963920996","https://openalex.org/W6629052376","https://openalex.org/W6696934422","https://openalex.org/W6696982659"],"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":{"We":[0,109],"present":[1],"a":[2,31,54,58,72],"recipe":[3,83],"for":[4,94],"training":[5,82,135],"acoustic":[6],"models":[7,121,127],"with":[8,33,46],"context":[9,34],"dependent":[10],"(CD)":[11],"phones":[12,37,62],"from":[13,39],"scratch":[14],"using":[15,63,112],"recurrent":[16],"neural":[17],"networks":[18],"(RNNs).":[19],"First,":[20],"we":[21,52],"use":[22],"the":[23,40,64,78,104,118],"connectionist":[24],"temporal":[25],"classification":[26],"(CTC)":[27],"technique":[28],"to":[29,56,76,125,132],"train":[30,71],"model":[32,68,75,93,106],"independent":[35],"(CI)":[36],"directly":[38],"written-domain":[41],"word":[42],"transcripts":[43],"by":[44,130],"aligning":[45],"all":[47],"possible":[48],"phonetic":[49],"verbalizations.":[50],"Then,":[51],"devise":[53],"mechanism":[55],"generate":[57],"set":[59],"of":[60,120],"CD":[61,73,95],"CTC":[65],"CI":[66],"phone":[67,74,96],"alignments":[69],"and":[70,100,122],"improve":[77,126],"accuracy.":[79],"This":[80],"end-to-end":[81],"does":[84,115],"not":[85,116],"require":[86],"any":[87],"previously":[88],"trained":[89],"GMM-HMM":[90],"or":[91,98,134],"DNN":[92],"generation":[97],"alignment,":[99],"thus":[101],"drastically":[102],"reduces":[103],"overall":[105],"building":[107],"time.":[108],"show":[110],"that":[111],"this":[113],"procedure":[114],"degrade":[117],"performance":[119],"allows":[123],"us":[124],"more":[128],"quickly":[129],"updates":[131],"pronunciations":[133],"data.":[136]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}