{"id":"https://openalex.org/W82856313","doi":"https://doi.org/10.21437/interspeech.2007-377","title":"Probabilistic latent speaker analysis for large vocabulary speech recognition","display_name":"Probabilistic latent speaker analysis for large vocabulary speech recognition","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W82856313","doi":"https://doi.org/10.21437/interspeech.2007-377","mag":"82856313"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-377","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dan Su","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112119747","display_name":"Huisheng Chi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huisheng Chi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075183307"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9387,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79922675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1162","last_page":"1165"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.752119243144989},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.6867515444755554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6866428256034851},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6105096936225891},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5640679597854614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5508496761322021},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5469444394111633},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5324462652206421},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5010390281677246},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5001401901245117},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5000710487365723},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.48100194334983826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4444187879562378},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4311867356300354},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43034815788269043},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41948097944259644},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16626155376434326},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15206027030944824},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07506275177001953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.752119243144989},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.6867515444755554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6866428256034851},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6105096936225891},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5640679597854614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5508496761322021},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5469444394111633},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5324462652206421},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5010390281677246},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5001401901245117},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5000710487365723},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.48100194334983826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4444187879562378},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4311867356300354},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43034815788269043},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41948097944259644},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16626155376434326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15206027030944824},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07506275177001953},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":1,"locations":[{"id":"doi:10.21437/interspeech.2007-377","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W67002875","https://openalex.org/W219295411","https://openalex.org/W2105594594","https://openalex.org/W2138324852","https://openalex.org/W2140669298","https://openalex.org/W2167797633"],"related_works":["https://openalex.org/W1505497582","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2412815366","https://openalex.org/W2181956362","https://openalex.org/W2136153680"],"abstract_inverted_index":{"Trajectory":[0],"folding":[1],"problem":[2],"is":[3,14,32,47,72],"intrinsic":[4],"for":[5,34],"HMM-based":[6],"speech":[7,37,50],"recognition":[8,38],"systems":[9,39],"in":[10,36],"which":[11],"each":[12],"state":[13],"modeled":[15],"by":[16],"a":[17,25,113],"mixture":[18],"of":[19,87],"Gaussian":[20,67,79],"components.":[21],"In":[22],"this":[23,42],"paper,":[24],"probabilistic":[26],"latent":[27],"semantic":[28],"analysis":[29,77],"(PLSA)-based":[30],"approach":[31],"proposed":[33],"use":[35],"to":[40,74,89],"alleviate":[41],"problem.":[43],"The":[44],"basic":[45],"idea":[46],"that":[48,99],"different":[49,59],"trajectories":[51],"are":[52],"strongly":[53],"correlated":[54],"with":[55],"speaker":[56],"variation,":[57],"and":[58,81,83,101,117],"speakers":[60,82],"may":[61],"have":[62],"high":[63],"scores":[64],"on":[65,105,112],"certain":[66],"components":[68,80],"consistently.":[69],"Thus,":[70],"PLSA":[71],"adopted":[73],"perform":[75],"co-occurrence":[76],"between":[78],"provide":[84],"additional":[85],"source":[86],"information":[88],"constrain":[90],"searching":[91],"path":[92],"during":[93],"decoding":[94],"procedure.":[95],"Experimental":[96],"results":[97],"show":[98],"11.2%":[100],"2.7%":[102],"relative":[103],"reduction":[104],"word":[106],"error":[107],"rate":[108],"can":[109],"be":[110],"achieved":[111],"homogeneous":[114],"test":[115],"set":[116],"the":[118],"2004":[119],"863":[120],"evaluation":[121],"set,":[122],"respectively.":[123]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}