{"id":"https://openalex.org/W2134486703","doi":"https://doi.org/10.1109/icassp.2011.5947453","title":"A simplified Subspace Gaussian Mixture to compact acoustic models for speech recognition","display_name":"A simplified Subspace Gaussian Mixture to compact acoustic models for speech recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2134486703","doi":"https://doi.org/10.1109/icassp.2011.5947453","mag":"2134486703"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947453","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":"preprint","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/A5061323881","display_name":"Mohamed Bouallegue","orcid":"https://orcid.org/0009-0008-7032-2773"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mohamed Bouallegue","raw_affiliation_strings":["LIA, University of Avignon, France"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, France","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017334281","display_name":"Driss Matrouf","orcid":null},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Driss Matrouf","raw_affiliation_strings":["LIA, University of Avignon, France"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, France","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050508708","display_name":"Georges Linar\u00e8s","orcid":"https://orcid.org/0000-0001-8049-9056"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Georges Linares","raw_affiliation_strings":["LIA, University of Avignon, France"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, France","institution_ids":["https://openalex.org/I198415970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061323881"],"corresponding_institution_ids":["https://openalex.org/I198415970"],"apc_list":null,"apc_paid":null,"fwci":2.6641,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91087901,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"4896","last_page":"4899"},"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":0.9994999766349792,"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":0.996999979019165,"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":0.8554979562759399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7669713497161865},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6908076405525208},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6819254159927368},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6359391808509827},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6196820735931396},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5831388831138611},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5307407975196838},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4487098157405853},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4197796583175659},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4166336953639984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3942781686782837},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30512845516204834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3042309880256653}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8554979562759399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669713497161865},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6908076405525208},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6819254159927368},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6359391808509827},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6196820735931396},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5831388831138611},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5307407975196838},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4487098157405853},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4197796583175659},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4166336953639984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3942781686782837},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30512845516204834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3042309880256653},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947453","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"},{"id":"pmh:oai:HAL:hal-01313109v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01313109","pdf_url":null,"source":{"id":"https://openalex.org/S4406922276","display_name":"INRIA a CCSD electronic archive server","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2011, Prague, Czech Republic. ⟨10.1109/ICASSP.2011.5947453⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W32979931","https://openalex.org/W84269282","https://openalex.org/W140642753","https://openalex.org/W1605997703","https://openalex.org/W2000592534","https://openalex.org/W2097944122","https://openalex.org/W2105594594","https://openalex.org/W2151402979","https://openalex.org/W2158069733","https://openalex.org/W2165108269","https://openalex.org/W2276283915","https://openalex.org/W6603425200"],"related_works":["https://openalex.org/W1992295166","https://openalex.org/W2143508933","https://openalex.org/W2735380212","https://openalex.org/W2018887914","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2122233706","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W1992225910"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,18],"applications":[2],"are":[3],"known":[4],"to":[5,48,91],"require":[6],"a":[7,53,103,113],"significant":[8],"amount":[9,55],"of":[10,29,37,56,60,66,85],"resources":[11],"(memory,":[12],"computing":[13],"power).":[14],"However,":[15],"embedded":[16],"speech":[17,39],"systems,":[19],"such":[20],"as":[21,144],"in":[22,120],"mobile":[23],"phones,":[24],"only":[25],"authorizes":[26],"few":[27,32],"KB":[28],"memory":[30],"and":[31,51,72,116],"MIPS.":[33],"In":[34,58,78],"the":[35,49,64,67,83,86,93,121,130,141,145],"context":[36],"HMM-based":[38],"recognizers,":[40],"each":[41],"HMM-state":[42],"distribution":[43],"is":[44,112],"modeled":[45],"independently":[46],"from":[47],"other":[50],"has":[52],"large":[54,71],"parameters.":[57],"spite":[59],"using":[61],"state-tying":[62],"techniques,":[63],"size":[65,96,133],"acoustic":[68,94,131,147],"models":[69,95],"stays":[70],"certain":[73],"redundancy":[74],"remains":[75],"between":[76],"states.":[77],"this":[79,125],"paper,":[80],"we":[81,127],"investigate":[82],"capacity":[84],"Subspace":[87],"Gaussian":[88],"Mixture":[89],"approach":[90],"reduce":[92],"while":[97],"keeping":[98],"good":[99],"performances.":[100],"We":[101],"introduce":[102],"simplification":[104],"concerning":[105],"state":[106],"specific":[107],"Gaussians":[108],"weights":[109],"estimation,":[110],"which":[111],"very":[114],"complex":[115],"time":[117],"consuming":[118],"procedure":[119],"original":[122],"approach.":[123],"With":[124],"approach,":[126],"show":[128],"that":[129],"model":[132],"can":[134],"be":[135],"reduced":[136],"by":[137],"92%":[138],"with":[139],"almost":[140],"same":[142],"performance":[143],"standard":[146],"modeling.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}