{"id":"https://openalex.org/W71101995","doi":"https://doi.org/10.21437/icslp.2002-386","title":"Models of speech dynamics in a segmental-HMM recognizer using intermediate linear representations","display_name":"Models of speech dynamics in a segmental-HMM recognizer using intermediate linear representations","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W71101995","doi":"https://doi.org/10.21437/icslp.2002-386","mag":"71101995"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-386","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Philip J.B. Jackson","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079477816","display_name":"Martin Russell","orcid":"https://orcid.org/0000-0002-8324-4961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin J. Russell","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022165330"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2784,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80869696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1253","last_page":"1256"},"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":0.9988999962806702,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.8331509828567505},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7476215362548828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7375737428665161},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.7064796686172485},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6307926177978516},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5730475783348083},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.529678463935852},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41906487941741943},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05176597833633423}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8331509828567505},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7476215362548828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7375737428665161},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7064796686172485},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6307926177978516},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5730475783348083},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.529678463935852},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41906487941741943},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05176597833633423},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"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":2,"locations":[{"id":"doi:10.21437/icslp.2002-386","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/2d1a0523-4d63-4442-9776-17981f85ebbc","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/2d1a0523-4d63-4442-9776-17981f85ebbc","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jackson, P & Russell, M 2002, 'Models of Speech Dynamics in a Segmental-HMM Recognizer Using Intermediate Linear Representations', Paper presented at Integrated Conference on Spoken Language Processing, ICSLP 2002, Denver, 1/09/02 pp. 1253-1256.","raw_type":"conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1998362482","https://openalex.org/W2083393647","https://openalex.org/W2092684968","https://openalex.org/W2118825896"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2967718153","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W165161405","https://openalex.org/W2019253074"],"abstract_inverted_index":{"A":[0],"theoretical":[1],"and":[2,20,44,56,68,84],"experimental":[3],"analysis":[4],"of":[5,24,73,81],"a":[6],"simple":[7],"multilevel":[8],"segmental":[9],"HMM":[10],"is":[11,26,87],"presented":[12],"in":[13],"which":[14],"the":[15,54],"relationship":[16],"between":[17,66],"symbolic":[18],"(phonetic)":[19],"surface":[21],"(acoustic)":[22],"representations":[23],"speech":[25,34],"regulated":[27],"by":[28,65,78],"an":[29],"intermediate":[30,51,82],"(articulatory)":[31],"layer,":[32],"where":[33],"dynamics":[35],"are":[36,48],"modeled":[37],"using":[38],"linear":[39,70],"trajectories.":[40],"Three":[41],"formant-based":[42],"parameterizations":[43],"measured":[45],"articulatory":[46],"positions":[47],"considered":[49],"as":[50],"representations,":[52],"from":[53],"TIMIT":[55],"MOCHA":[57],"corpora":[58],"respectively.":[59],"The":[60],"articulatory-to-acoustic":[61],"mapping":[62],"was":[63],"performed":[64],"1":[67],"49":[69],"transformations.":[71],"Results":[72],"phone-classification":[74],"experiments":[75],"demonstrate":[76],"that,":[77],"appropriate":[79],"choice":[80],"parameterization":[83],"mappings,":[85],"it":[86],"possible":[88],"to":[89,92],"achieve":[90],"close":[91],"optimal":[93],"performance.":[94]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}