{"id":"https://openalex.org/W68437168","doi":null,"title":"A Segmental HMM for Speech Waveforms","display_name":"A Segmental HMM for Speech Waveforms","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W68437168","mag":"68437168"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.7333","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.7333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/~roweis/papers/TRseghmm.ps.gz","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5079669827","display_name":"Kannan Achan","orcid":"https://orcid.org/0009-0000-9186-3175","observed_orcids":["https://orcid.org/0009-0000-9186-3175"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kannan Achan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003010184","display_name":"Sam T. Roweis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Roweis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sam Roweis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Roweis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sam Roweis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Roweis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003361977","display_name":"Brendan J. Frey","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brendan Frey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5604,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92374429,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5375999808311462,"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":0.5375999808311462,"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":0.45829999446868896,"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/T10863","display_name":"Voice and Speech Disorders","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/voiced-unvoiced-detection","display_name":"voiced/unvoiced detection","score":0.8640000224113464},{"id":"https://openalex.org/keywords/pitch-tracking","display_name":"pitch tracking","score":0.9340000152587891},{"id":"https://openalex.org/keywords/generative-probabilistic-models","display_name":"probabilistic generative models","score":0.9319999814033508},{"id":"https://openalex.org/keywords/spectral-estimation","display_name":"spectral estimation","score":0.6200000047683716}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7852296829223633},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6872363686561584},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6706780195236206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.631024956703186},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.606399416923523},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4962058663368225},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.42528772354125977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34924182295799255},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0812135636806488},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.7333","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.7333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/~roweis/papers/TRseghmm.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.7662","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.7662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.psi.toronto.edu/~kannan/Segmental/TR/TRseghmmV2.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.8388","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.8388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.psi.toronto.edu/~kannan/Segmental/TR/TRseghmm.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W23669922","https://openalex.org/W2098920026","https://openalex.org/W2123782934","https://openalex.org/W2159323669"],"related_works":["https://openalex.org/W2157328787","https://openalex.org/W7098355909","https://openalex.org/W7132966644","https://openalex.org/W1998887212","https://openalex.org/W7100769768","https://openalex.org/W1985350076","https://openalex.org/W1793242924","https://openalex.org/W292024111","https://openalex.org/W4230779539","https://openalex.org/W4410991085"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,41],"purely":[3],"time":[4],"domain":[5],"approach":[6],"to":[7],"speech":[8,47],"processing":[9],"which":[10],"identifies":[11],"waveform":[12],"samples":[13],"at":[14,25],"the":[15,26,51],"boundaries":[16,27,37],"between":[17,28],"glottal":[18],"pulse":[19],"periods":[20],"(in":[21],"voiced":[22],"speech)":[23],"or":[24],"unvoiced":[29],"segments.":[30],"An":[31],"e#cient":[32],"algorithm":[33],"for":[34],"inferring":[35],"these":[36],"is":[38],"derived":[39],"from":[40],"simple":[42],"probabilistic":[43],"generative":[44],"model":[45],"of":[46,50],"and":[48,61],"state":[49],"art":[52],"results":[53],"are":[54],"presented":[55],"on":[56],"pitch":[57],"tracking,":[58],"voiced/unvoiced":[59],"detection":[60],"timescale":[62],"modification.":[63]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-27T00:00:00"}
