{"id":"https://openalex.org/W2550260012","doi":"https://doi.org/10.1109/spcom.2016.7746648","title":"Improved phone-cluster adaptive training acoustic model","display_name":"Improved phone-cluster adaptive training acoustic model","publication_year":2016,"publication_date":"2016-06-01","ids":{"openalex":"https://openalex.org/W2550260012","doi":"https://doi.org/10.1109/spcom.2016.7746648","mag":"2550260012"},"language":"en","primary_location":{"id":"doi:10.1109/spcom.2016.7746648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2016.7746648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Signal Processing and Communications (SPCOM)","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/A5074777875","display_name":"Neethu Mariam Joy","orcid":"https://orcid.org/0000-0003-2460-5189"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Neethu Mariam Joy","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Madras Chennai, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Madras Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Umesh","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Madras Chennai, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Madras Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005220677","display_name":"Basil Abraham","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Basil Abraham","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Madras Chennai, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Madras Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044932967","display_name":"K Navneeth","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K Navneeth","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Madras Chennai, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Madras Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074777875"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07527998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9975000023841858,"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":0.9959999918937683,"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/subspace-topology","display_name":"Subspace topology","score":0.901671290397644},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.895287275314331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7562447190284729},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6814432144165039},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5794601440429688},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.49671822786331177},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.44034045934677124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.302359938621521},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15974679589271545}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.901671290397644},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.895287275314331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562447190284729},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6814432144165039},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5794601440429688},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.49671822786331177},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.44034045934677124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.302359938621521},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15974679589271545},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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":1,"locations":[{"id":"doi:10.1109/spcom.2016.7746648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2016.7746648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Signal Processing and Communications (SPCOM)","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":11,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1805340023","https://openalex.org/W1981706894","https://openalex.org/W2018375232","https://openalex.org/W2021775343","https://openalex.org/W2069631319","https://openalex.org/W2094725813","https://openalex.org/W2136879537","https://openalex.org/W2147794814","https://openalex.org/W2151402979","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W1980381208","https://openalex.org/W2364594919","https://openalex.org/W2167092671","https://openalex.org/W1861706286","https://openalex.org/W2219338811","https://openalex.org/W2149583853","https://openalex.org/W2143002539","https://openalex.org/W2550260012","https://openalex.org/W2151402979","https://openalex.org/W1578916557"],"abstract_inverted_index":{"Phone-cluster":[0],"adaptive":[1,14],"training":[2,15],"(Phone-CAT)":[3],"is":[4,77,90],"a":[5,65,97],"subspace":[6,18,31,67,73,106],"based":[7],"acoustic":[8,62],"modeling":[9],"technique":[10],"inspired":[11],"from":[12],"cluster":[13],"(CAT)":[16],"and":[17,35],"Gaussian":[19],"mixture":[20],"model":[21,42,100,117,153],"(SGMM).":[22],"This":[23,116],"paper":[24],"explores":[25],"three":[26],"extensions,":[27],"viz.,":[28],"increasing":[29],"phonetic":[30,72,105],"dimension,":[32],"including":[33],"sub-states":[34],"speaker":[36],"subspace,":[37],"to":[38,43,79,82,93,108,122],"the":[39,71,83,87,104,111,124,130,155,158],"basic":[40,134,151],"Phone-CAT":[41,76,99,152],"improve":[44],"its":[45],"recognition":[46,148],"performance.":[47],"The":[48],"latter":[49],"two":[50],"extensions":[51],"are":[52],"similar":[53,66],"in":[54,133,147],"implementation":[55],"as":[56,60],"that":[57,109],"of":[58,75,85,110,113,129,142,150,157],"SGMM":[59],"both":[61],"models":[63],"share":[64],"framework.":[68],"But,":[69],"since":[70],"dimension":[74,107],"constrained":[78],"be":[80,120],"equal":[81],"number":[84,112],"monophones,":[86],"first":[88],"extension":[89],"not":[91],"straightforward":[92],"implement.":[94],"We":[95],"propose":[96],"Two-stage":[98],"where":[101],"we":[102],"increase":[103],"monophone":[114],"states.":[115],"will":[118],"still":[119],"able":[121],"retain":[123],"center":[125],"phone":[126],"capturing":[127],"property":[128],"state-specific":[131],"vectors":[132],"Phone-CAT.":[135],"Experiments":[136],"done":[137],"on":[138],"33-hour":[139],"train":[140],"subset":[141],"Switchboard":[143],"database":[144],"shows":[145],"improvements":[146],"performance":[149],"with":[154],"inclusion":[156],"proposed":[159],"extensions.":[160]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}