{"id":"https://openalex.org/W75019816","doi":"https://doi.org/10.21437/interspeech.2008-308","title":"Monte Carlo model-space noise adaptation for speech recognition","display_name":"Monte Carlo model-space noise adaptation for speech recognition","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W75019816","doi":"https://doi.org/10.21437/interspeech.2008-308","mag":"75019816"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-308","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},"type":"conference-paper","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/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1281","last_page":"1284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9919000267982483,"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/speech-recognition","display_name":"Speech recognition","score":0.6732273101806641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6608098745346069},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6513442397117615},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6460156440734863},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5725309252738953},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5192922949790955},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.5113705992698669},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4269362986087799},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.42050987482070923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4200621247291565},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3643321990966797},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18208754062652588},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.14144903421401978},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11314418911933899},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06443142890930176}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6732273101806641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6608098745346069},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6513442397117615},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6460156440734863},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5725309252738953},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5192922949790955},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.5113705992698669},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4269362986087799},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42050987482070923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4200621247291565},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3643321990966797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18208754062652588},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.14144903421401978},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11314418911933899},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06443142890930176},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2008-308","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W84880661","https://openalex.org/W105750483","https://openalex.org/W174003511","https://openalex.org/W1545736995","https://openalex.org/W2002342963","https://openalex.org/W2063291689","https://openalex.org/W2090861223","https://openalex.org/W2111093880","https://openalex.org/W2126597753","https://openalex.org/W2149648698"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2372625757","https://openalex.org/W4313178214","https://openalex.org/W2970653563","https://openalex.org/W3093766508","https://openalex.org/W2012393389","https://openalex.org/W2899717399","https://openalex.org/W2048014685","https://openalex.org/W2370972896"],"abstract_inverted_index":{"We":[0,59],"describe":[1],"a":[2,18,86,94],"Monte":[3],"Carlo":[4],"method":[5,16],"for":[6],"model-space":[7,40],"noise":[8,20,66,92],"adaptation":[9,100],"of":[10,63],"Gaussian":[11],"mixture":[12],"models":[13],"(GMMs).":[14],"This":[15],"combines":[17],"single-Gaussian":[19],"model":[21,26],"with":[22],"the":[23,61,65,69],"GMM":[24],"speech":[25,72],"to":[27,35,46,54],"produce":[28],"an":[29],"adapted":[30],"model.":[31],"It":[32],"is":[33],"similar":[34],"Parallel":[36],"Model":[37],"Combination":[38],"or":[39],"Joint,":[41],"except":[42],"that":[43,96],"it":[44,78],"applies":[45],"spliced":[47],"and":[48,71,82],"projected":[49],"MFCC":[50,55],"features":[51],"rather":[52,74],"than":[53,75],"plus":[56],"dynamic":[57],"features.":[58],"demonstrate":[60],"necessity":[62],"reestimating":[64],"using":[67,93],"both":[68],"silence":[70,80],"frames":[73],"just":[76],"estimating":[77],"from":[79],"frames,":[81],"obtain":[83],"improvements":[84],"on":[85],"matched":[87],"test":[88],"set":[89],"without":[90],"added":[91],"system":[95],"includes":[97],"all":[98],"standard":[99],"techniques.":[101]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}