{"id":"https://openalex.org/W1839403150","doi":"https://doi.org/10.1109/icassp.1997.596168","title":"Utterance dependent parametric warping for a talker-independent HMM-based recognizer","display_name":"Utterance dependent parametric warping for a talker-independent HMM-based recognizer","publication_year":2002,"publication_date":"2002-11-22","ids":{"openalex":"https://openalex.org/W1839403150","doi":"https://doi.org/10.1109/icassp.1997.596168","mag":"1839403150"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1997.596168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1997.596168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1997 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/A5009285575","display_name":"Daniel Mashao","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"D.J. Mashao","raw_affiliation_strings":["LEMS, Division of Engineering, Brown University, Providence, RI, USA"],"affiliations":[{"raw_affiliation_string":"LEMS, Division of Engineering, Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019203445","display_name":"John Adcock","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.E. Adcock","raw_affiliation_strings":["LEMS, Division of Engineering, Brown University, Providence, RI, USA"],"affiliations":[{"raw_affiliation_string":"LEMS, Division of Engineering, Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009285575"],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09224883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"1235","last_page":"1238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8035759925842285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7645691633224487},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7361424565315247},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.7167689800262451},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6397890448570251},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.534596860408783},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5246729254722595},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5108770728111267},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4999101161956787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39709198474884033},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38439613580703735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12827634811401367},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06946703791618347}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8035759925842285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645691633224487},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7361424565315247},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.7167689800262451},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6397890448570251},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.534596860408783},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5246729254722595},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5108770728111267},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4999101161956787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39709198474884033},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38439613580703735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12827634811401367},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06946703791618347}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.1997.596168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1997.596168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1997 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.56.13","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.56.13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.lems.brown.edu/pub/speech/papers/icsp97.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W2104663520","https://openalex.org/W2106119541","https://openalex.org/W2139411757","https://openalex.org/W2352579185"],"related_works":["https://openalex.org/W249497648","https://openalex.org/W2419138286","https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W2507549656","https://openalex.org/W2050318184","https://openalex.org/W2182848507","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2387825067"],"abstract_inverted_index":{"In":[0],"an":[1],"effort":[2],"to":[3,22,35,84,100],"improve":[4],"the":[5,24,75,78,91,95,102,105,109,122],"recognition":[6,26],"performance":[7,27],"of":[8,29,44],"talker-independent":[9,36],"speech":[10],"systems,":[11],"many":[12],"adaptive":[13],"methods":[14,19],"have":[15],"been":[16],"proposed.":[17],"The":[18],"generally":[20],"seek":[21],"exploit":[23],"higher":[25],"rate":[28],"talker-dependent":[30],"systems":[31],"and":[32,74,121],"extend":[33],"it":[34],"systems.":[37],"This":[38],"is":[39,68,81,98],"achieved":[40],"by":[41],"some":[42],"form":[43],"placing":[45],"talkers":[46],"into":[47,116],"several":[48,71],"categories,":[49],"usually":[50],"using":[51,70],"gender":[52],"or":[53],"vocal-tract":[54],"size.":[55],"We":[56],"investigate":[57],"a":[58,86],"similar":[59],"idea,":[60],"but":[61],"categorize":[62],"each":[63],"utterance":[64,67],"independently.":[65],"An":[66],"processed":[69],"spectral":[72,92,106],"compressions,":[73],"compression":[76,93],"with":[77,94],"maximum":[79,96],"likelihood":[80,97],"then":[82],"used":[83,99],"train":[85],"better":[87],"model.":[88],"For":[89],"testing,":[90],"decode":[101],"utterance.":[103],"While":[104],"compressions":[107],"divided":[108],"utterances":[110],"well,":[111],"this":[112],"did":[113],"not":[114],"translate":[115],"significant":[117],"improvement":[118],"in":[119],"performance,":[120],"computational":[123],"cost":[124],"increase":[125],"was":[126],"significant.":[127]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}