{"id":"https://openalex.org/W2401271337","doi":"https://doi.org/10.21437/interspeech.2012-594","title":"Automatic speech segmentation using probabilistic latent component modeling","display_name":"Automatic speech segmentation using probabilistic latent component modeling","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2401271337","doi":"https://doi.org/10.21437/interspeech.2012-594","mag":"2401271337"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-594","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100670911","display_name":"Sayan Ghosh","orcid":"https://orcid.org/0000-0001-8758-7657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sayan Ghosh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069425803","display_name":"T.V. Sreenivas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thippur V. Sreenivas","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":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2262","last_page":"2265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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":0.995199978351593,"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":0.9908000230789185,"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/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/timit","display_name":"TIMIT","score":0.814368486404419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6893887519836426},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6614407896995544},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6454553604125977},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5642523169517517},{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.5622367858886719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5085867643356323},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5045298337936401},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.48864322900772095},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45569083094596863},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.45305174589157104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43817469477653503},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4295051097869873},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35180413722991943},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.27462562918663025},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17818930745124817},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07381489872932434}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.814368486404419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6893887519836426},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6614407896995544},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6454553604125977},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5642523169517517},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.5622367858886719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085867643356323},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5045298337936401},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.48864322900772095},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45569083094596863},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.45305174589157104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43817469477653503},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4295051097869873},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35180413722991943},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27462562918663025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17818930745124817},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07381489872932434},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-594","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:47278","is_oa":false,"landing_page_url":"http://eprints.iisc.ac.in/47278/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2990278625","https://openalex.org/W1993499045","https://openalex.org/W2147978301","https://openalex.org/W1980604799","https://openalex.org/W2052112670","https://openalex.org/W2474633151","https://openalex.org/W2150473580","https://openalex.org/W2727244960","https://openalex.org/W2048014685","https://openalex.org/W3160080723"],"abstract_inverted_index":{"Latent":[0,7,27],"variable":[1],"methods,":[2],"such":[3],"as":[4,38],"PLCA":[5],"(Probabilistic":[6,26],"Component":[8,28],"Analysis)":[9],"have":[10],"been":[11],"successfully":[12],"used":[13],"for":[14],"analysis":[15],"of":[16,35,81,129],"non-negative":[17],"signal":[18,44],"representations.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"formulate":[24],"PLCS":[25,89,102],"Segmentation),":[29],"which":[30],"models":[31],"each":[32,66],"time":[33],"frame":[34],"a":[36,39,52,62,71,94],"spectrogram":[37],"spectral":[40],"distribution.":[41],"Given":[42],"the":[43,46,59,79,115,120,130],"spectrogram,":[45],"segmentation":[47,100,133],"boundaries":[48],"are":[49],"estimated":[50],"using":[51,85],"maximum-likelihood":[53],"approach.":[54],"For":[55],"an":[56],"efficient":[57],"solution,":[58],"algorithm":[60],"imposes":[61],"hard":[63,76],"constraint":[64,77],"that":[65,119],"segment":[67],"is":[68,123],"modelled":[69],"by":[70],"single":[72],"latent":[73],"component.":[74],"The":[75,88],"facilitates":[78],"solution":[80],"ML":[82,99],"boundary":[83],"estimation":[84],"dynamic":[86],"programming.":[87],"framework":[90],"does":[91],"not":[92],"impose":[93],"parametric":[95],"assumption":[96],"unlike":[97],"earlier":[98],"techniques.":[101],"can":[103],"be":[104],"naturally":[105],"extended":[106],"to":[107,126],"model":[108],"coarticulation":[109],"between":[110],"successive":[111],"phones.":[112],"Experiments":[113],"on":[114],"TIMIT":[116],"corpus":[117],"show":[118],"proposed":[121],"technique":[122],"promising":[124],"compared":[125],"most":[127],"state":[128],"art":[131],"speech":[132],"algorithms.":[134]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}