{"id":"https://openalex.org/W2157328787","doi":"https://doi.org/10.1109/icassp.2005.1416280","title":"A Segment-Based Probabilistic Generative Model of Speech","display_name":"A Segment-Based Probabilistic Generative Model of Speech","publication_year":2006,"publication_date":"2006-10-04","ids":{"openalex":"https://openalex.org/W2157328787","doi":"https://doi.org/10.1109/icassp.2005.1416280","mag":"2157328787"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1416280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1416280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5079669827","display_name":"Kannan Achan","orcid":"https://orcid.org/0009-0000-9186-3175"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"K. Achan","raw_affiliation_strings":["Departments of Computer Science and ECE, University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Departments of Computer Science and ECE, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003010184","display_name":"Sam T. Roweis","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"S. Roweis","raw_affiliation_strings":["Departments of Computer Science and ECE, University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Departments of Computer Science and ECE, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061237128","display_name":"Aaron Hertzmann","orcid":"https://orcid.org/0000-0001-9667-0292"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"A. Hertzmann","raw_affiliation_strings":["Departments of Computer Science and ECE, University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Departments of Computer Science and ECE, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003361977","display_name":"Brendan J. Frey","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"B. Frey","raw_affiliation_strings":["Departments of Computer Science and ECE, University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Departments of Computer Science and ECE, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079669827"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":1.9081,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86144308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"221","last_page":"224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7344399690628052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7035146355628967},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6664034724235535},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.650745153427124},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6227105259895325},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6135979294776917},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5908967852592468},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5890994071960449},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5098246932029724},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.47805291414260864},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4501190781593323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.437056303024292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7344399690628052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7035146355628967},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6664034724235535},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.650745153427124},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6227105259895325},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6135979294776917},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5908967852592468},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5890994071960449},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5098246932029724},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.47805291414260864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4501190781593323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.437056303024292},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2005.1416280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1416280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.7616","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.7616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dgp.toronto.edu/papers/kachan_ICASSP2005.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W23669922","https://openalex.org/W68437168","https://openalex.org/W2032371708","https://openalex.org/W2091425152","https://openalex.org/W2133908567","https://openalex.org/W2162977283","https://openalex.org/W2394962911","https://openalex.org/W2428180336","https://openalex.org/W4285719527","https://openalex.org/W6602797164","https://openalex.org/W6680017764","https://openalex.org/W6684120061"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495","https://openalex.org/W4387506531"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,51],"purely":[3],"time":[4],"domain":[5],"approach":[6],"to":[7],"speech":[8],"processing":[9],"which":[10],"identifies":[11],"waveform":[12],"samples":[13],"at":[14,25],"the":[15,26,40,78,85],"boundaries":[16,27,37],"between":[17],"glottal":[18],"pulse":[19],"periods":[20],"(in":[21],"voiced":[22,44],"speech)":[23],"or":[24],"of":[28,43],"unvoiced":[29,46],"segments.":[30],"An":[31],"efficient":[32],"algorithm":[33],"for":[34],"inferring":[35],"these":[36,69],"and":[38,45,65,71],"estimating":[39],"average":[41],"spectra":[42],"regions":[47],"is":[48],"derived":[49],"from":[50],"simple":[52],"probabilistic":[53],"generative":[54],"model.":[55,86],"Competitive":[56],"results":[57],"are":[58],"presented":[59],"on":[60],"pitch":[61],"tracking,":[62],"voiced/unvoiced":[63],"detection":[64],"timescale":[66],"modification;":[67],"all":[68],"tasks":[70],"several":[72],"others":[73],"can":[74],"be":[75],"performed":[76],"using":[77],"single":[79],"segmentation":[80],"provided":[81],"by":[82],"inference":[83],"in":[84]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
