{"id":"https://openalex.org/W2121783024","doi":"https://doi.org/10.1109/icassp.1987.1169454","title":"Automatic speech recognition via pseudo-independent marginal mixtures","display_name":"Automatic speech recognition via pseudo-independent marginal mixtures","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W2121783024","doi":"https://doi.org/10.1109/icassp.1987.1169454","mag":"2121783024"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1987.1169454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1987.1169454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5063150637","display_name":"Arthur N\u00e1das","orcid":"https://orcid.org/0000-0002-6893-6759"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Nadas","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007586881","display_name":"D. Nahamoo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Nahamoo","raw_affiliation_strings":["Department of Computer Sciences, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.17959741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"1285","last_page":"1287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7651146650314331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6283902525901794},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6240765452384949},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5684686899185181},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.5311428904533386},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5155653953552246},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4544021785259247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4500733017921448},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.44525086879730225},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.423151433467865},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4134637415409088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38394397497177124},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.313510924577713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651146650314331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6283902525901794},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6240765452384949},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5684686899185181},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.5311428904533386},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5155653953552246},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4544021785259247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4500733017921448},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44525086879730225},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.423151433467865},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4134637415409088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38394397497177124},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.313510924577713},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1987.1169454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1987.1169454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1579558060","https://openalex.org/W1847689439","https://openalex.org/W1968127489","https://openalex.org/W1981367467","https://openalex.org/W1983768315"],"related_works":["https://openalex.org/W1655266410","https://openalex.org/W2389051085","https://openalex.org/W2330343234","https://openalex.org/W1901012776","https://openalex.org/W2463883322","https://openalex.org/W2138195696","https://openalex.org/W2121067345","https://openalex.org/W3209251257","https://openalex.org/W2545295736","https://openalex.org/W2125163191"],"abstract_inverted_index":{"Statistical":[0],"models":[1],"(prototypes)":[2],"for":[3,58,82,138,146],"the":[4,21,29,38,43,46,63,70],"multivariate":[5,116],"probability":[6],"distribution":[7],"of":[8,11,23,31,133,142],"vectors":[9,24],"(frames)":[10],"speech":[12,35,121],"parameters":[13],"may":[14],"be":[15],"utilized":[16],"in":[17,97,109],"various":[18],"ways.":[19],"If":[20],"stream":[22,66],"is":[25,67],"passed":[26,68],"directly":[27],"to":[28,69],"decoder":[30],"a":[32,49,80,91,95,103,110,114,134,152],"continuous":[33],"parameter":[34],"recognizer":[36,47],"then":[37,54],"prototypes":[39,126],"are":[40,56,74],"used":[41,57],"by":[42,129],"decoder;":[44,71],"if":[45],"has":[48],"time-synchronous":[50],"labeling":[51,153],"acoustic":[52,154],"processor":[53],"they":[55],"vector":[59],"quantization":[60],"(labeling)":[61],"and":[62,106,140],"resulting":[64],"label":[65],"other":[72],"uses":[73],"possible":[75],"as":[76,90,102,113],"well.":[77],"We":[78,119,148],"present":[79,149],"method":[81,87],"constructing":[83],"such":[84],"prototypes.":[85],"This":[86],"was":[88],"chosen":[89],"compromise":[92],"between":[93],"describing":[94,107],"prototype":[96],"an":[98,143],"assumption":[99],"free":[100],"way":[101,112],"nonparametric":[104],"density":[105],"it":[108],"convenient":[111],"simple":[115],"Gaussian":[117],"density.":[118],"describe":[120],"recognition":[122],"experiments":[123],"where":[124],"our":[125,162],"were":[127],"trained":[128],"iteratively":[130],"interleaving":[131],"steps":[132,141],"K-MEANS":[135],"type":[136],"algorithm":[137,145],"clustering":[139],"EM":[144],"reestimation.":[147],"results":[150],"(using":[151],"processor)":[155],"having":[156],"significantly":[157],"fewer":[158],"decoding":[159],"errors":[160],"than":[161],"previous":[163],"methods":[164],"do.":[165]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}