{"id":"https://openalex.org/W2160323565","doi":"https://doi.org/10.1109/icassp.2011.5947486","title":"Dirichlet Mixture Models of neural net posteriors for HMM-based speech recognition","display_name":"Dirichlet Mixture Models of neural net posteriors for HMM-based speech recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2160323565","doi":"https://doi.org/10.1109/icassp.2011.5947486","mag":"2160323565"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947486","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5066217200","display_name":"V. Balakrishnan","orcid":"https://orcid.org/0000-0003-3244-2711"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Balakrishnan V","raw_affiliation_strings":["Dept. of Electrical & Computer Engineering, The Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical & Computer Engineering, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109860004","display_name":"G. S. V. S. Sivaram","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G.S.V.S. Sivaram","raw_affiliation_strings":["Dept. of Electrical & Computer Engineering, The Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical & Computer Engineering, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Dept. of Electrical & Computer Engineering, The Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical & Computer Engineering, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066217200"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.7103,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.87335059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"3","issue":null,"first_page":"5028","last_page":"5031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9993000030517578,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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":0.9757999777793884,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7830657958984375},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.737977147102356},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.6755706071853638},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6716924905776978},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.6263089776039124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.592313826084137},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.5154076814651489},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5037791132926941},{"id":"https://openalex.org/keywords/simplex","display_name":"Simplex","score":0.42189860343933105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3893986940383911},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33040621876716614},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10606476664543152}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7830657958984375},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.737977147102356},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.6755706071853638},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6716924905776978},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.6263089776039124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.592313826084137},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.5154076814651489},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5037791132926941},{"id":"https://openalex.org/C62438384","wikidata":"https://www.wikidata.org/wiki/Q331350","display_name":"Simplex","level":2,"score":0.42189860343933105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3893986940383911},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33040621876716614},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10606476664543152},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947486","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W98826895","https://openalex.org/W190008395","https://openalex.org/W197151588","https://openalex.org/W1980501707","https://openalex.org/W2049633694","https://openalex.org/W2090861223","https://openalex.org/W2165712214","https://openalex.org/W2166698530","https://openalex.org/W4300859697","https://openalex.org/W6604030440","https://openalex.org/W6607826182","https://openalex.org/W6607944266"],"related_works":["https://openalex.org/W2113823560","https://openalex.org/W2052112670","https://openalex.org/W2474633151","https://openalex.org/W3166198130","https://openalex.org/W2059343102","https://openalex.org/W1882901045","https://openalex.org/W3116791621","https://openalex.org/W2048014685","https://openalex.org/W74847246","https://openalex.org/W3160080723"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,16,37,102],"novel":[6],"technique":[7,114],"for":[8],"modeling":[9],"the":[10,22,26,52,70,94,97,112,116],"posterior":[11,32],"probability":[12,33,38,98],"estimates":[13],"obtained":[14],"from":[15],"neural":[17],"net":[18],"work":[19],"directly":[20],"in":[21,48,59],"HMM":[23],"framework":[24],"using":[25,45,78],"Dirichlet":[27],"Mixture":[28,80],"Models":[29,81],"(DMMs).":[30],"Since":[31],"vectors":[34,99],"lie":[35,100],"on":[36,101],"simplex":[39],"their":[40],"distribution":[41],"can":[42,56],"be":[43,57],"modeled":[44],"DMMs.":[46],"Being":[47],"an":[49,60],"exponential":[50],"family,":[51],"parameters":[53,88],"of":[54,87],"DMMs":[55],"estimated":[58],"efficient":[61],"manner.":[62],"Conventional":[63],"approaches":[64],"like":[65],"TANDEM":[66,118],"attempt":[67],"to":[68],"gaussianize":[69],"posteriors":[71],"by":[72],"suitable":[73],"transforms":[74],"and":[75],"model":[76],"them":[77],"Gaussian":[79],"(GMMs).":[82],"This":[83],"requires":[84],"more":[85],"number":[86],"as":[89],"it":[90],"does":[91],"not":[92],"exploit":[93],"fact":[95],"that":[96,111],"simplex.":[103],"We":[104],"demonstrate":[105],"through":[106],"TIMIT":[107],"phoneme":[108],"recognition":[109],"experiments":[110],"proposed":[113],"outperforms":[115],"conventional":[117],"approach.":[119]},"counts_by_year":[{"year":2013,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}