{"id":"https://openalex.org/W2408441945","doi":"https://doi.org/10.1109/icassp.2016.7472645","title":"How neural network features and depth modify statistical properties of HMM acoustic models","display_name":"How neural network features and depth modify statistical properties of HMM acoustic models","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2408441945","doi":"https://doi.org/10.1109/icassp.2016.7472645","mag":"2408441945"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472645","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/A5026262869","display_name":"Suman Ravuri","orcid":"https://orcid.org/0000-0002-7481-7633"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suman Ravuri","raw_affiliation_strings":["International Computer Science Institute","University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025957537","display_name":"Steven Wegmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I4210119657","display_name":"Semantic Designs (United States)","ror":"https://ror.org/025rxfw41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210119657"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Wegmann","raw_affiliation_strings":["International Computer Science Institute","Semantic Machines, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"Semantic Machines, Inc","institution_ids":["https://openalex.org/I4210119657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4416,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78435131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5080","last_page":"5084"},"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":0.9980000257492065,"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":0.9951000213623047,"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":0.8076599836349487},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8005728125572205},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6701710224151611},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.629092812538147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5873124599456787},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5564501881599426},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5478451251983643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5323455929756165},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.5184433460235596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3830995559692383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3557698726654053},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2904857397079468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076599836349487},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8005728125572205},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6701710224151611},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.629092812538147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5873124599456787},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5564501881599426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5478451251983643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5323455929756165},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.5184433460235596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3830995559692383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3557698726654053},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2904857397079468},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/icassp.2016.7472645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472645","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W75470185","https://openalex.org/W1513984940","https://openalex.org/W1559401186","https://openalex.org/W1591607137","https://openalex.org/W1978741356","https://openalex.org/W2048608953","https://openalex.org/W2117897510","https://openalex.org/W2122514667","https://openalex.org/W2124181495","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2165712214","https://openalex.org/W2171631590","https://openalex.org/W2277634955","https://openalex.org/W2293858598","https://openalex.org/W2295676751","https://openalex.org/W2395655916","https://openalex.org/W2395981916","https://openalex.org/W2405662050","https://openalex.org/W2408093180","https://openalex.org/W6603060513","https://openalex.org/W6694900938","https://openalex.org/W6697607580","https://openalex.org/W6713378355"],"related_works":["https://openalex.org/W2052515325","https://openalex.org/W2050948537","https://openalex.org/W2767646790","https://openalex.org/W2364370872","https://openalex.org/W2352041579","https://openalex.org/W2053269318","https://openalex.org/W1488006380","https://openalex.org/W2138381686","https://openalex.org/W2349769824","https://openalex.org/W2141585124"],"abstract_inverted_index":{"Tandem":[0],"neural":[1,37,110],"network":[2,38,111],"features,":[3,109],"especially":[4],"ones":[5],"trained":[6],"with":[7,41],"more":[8],"than":[9],"one":[10],"hidden":[11],"layer,":[12],"have":[13],"improved":[14],"word":[15],"recognition":[16,25],"performance,":[17],"but":[18],"why":[19],"these":[20],"features":[21,39,112],"improve":[22],"automatic":[23],"speech":[24],"systems":[26],"is":[27,126],"not":[28],"completely":[29],"understood.":[30],"In":[31],"this":[32],"work,":[33],"we":[34,55,86],"study":[35],"how":[36],"cope":[40],"the":[42,45,53,74,79,101,120,130,135],"mismatch":[43,99],"between":[44],"underlying":[46],"stochastic":[47],"process":[48],"inherent":[49],"in":[50],"speech,":[51],"and":[52,82,104,137],"models":[54],"use":[56,62],"to":[57,72,97,106,152],"represent":[58],"that":[59,92,134],"process.":[60],"We":[61,90],"a":[63],"novel":[64],"resampling":[65],"framework,":[66],"which":[67,148],"re-samples":[68],"test":[69],"set":[70],"data":[71],"match":[73],"conditional":[75],"independence":[76],"assumptions":[77,118,144],"of":[78,119],"acoustic":[80],"model,":[81,132],"measure":[83],"performance":[84],"as":[85],"break":[87],"those":[88],"assumptions.":[89],"discover":[91],"depth":[93],"provides":[94],"modest":[95],"robustness":[96],"data/model":[98],"at":[100],"state":[102],"level,":[103],"compared":[105],"standard":[107],"MFCC":[108],"actually":[113],"fix":[114],"poor":[115],"duration":[116,123],"modeling":[117,124],"HMM.":[121],"The":[122],"problem":[125],"also":[127],"fixed":[128],"by":[129],"language":[131,138],"suggesting":[133],"dictionary":[136],"model":[139],"make":[140],"very":[141],"strong":[142],"implicit":[143],"about":[145],"phone":[146],"length,":[147],"may":[149],"now":[150],"need":[151],"be":[153],"revisited.":[154]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}