{"id":"https://openalex.org/W96727869","doi":"https://doi.org/10.21437/interspeech.2004-169","title":"Automatic transcription of continuous speech using unsupervised and incremental training","display_name":"Automatic transcription of continuous speech using unsupervised and incremental training","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W96727869","doi":"https://doi.org/10.21437/interspeech.2004-169","mag":"96727869"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-169","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5078835726","display_name":"G.L. Sarada Ghadiyaram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G.L. Sarada Ghadiyaram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044488408","display_name":"N. Nagarajan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N. Hemalatha Nagarajan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047358973","display_name":"Thyagarajan Thangavelu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. Nagarajan Thangavelu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032418366","display_name":"Hema A. Murthy","orcid":"https://orcid.org/0000-0003-3611-6550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hema A. Murthy","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":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"405","last_page":"408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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/speech-recognition","display_name":"Speech recognition","score":0.7725468873977661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7595599889755249},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6721425652503967},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6307857632637024},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6066830158233643},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6057462096214294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5343450903892517},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47415655851364136},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.445832759141922},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44317135214805603},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.41088417172431946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39526844024658203},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3925924301147461}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7725468873977661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595599889755249},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6721425652503967},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6307857632637024},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6066830158233643},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6057462096214294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343450903892517},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47415655851364136},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.445832759141922},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44317135214805603},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.41088417172431946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39526844024658203},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3925924301147461},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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":1,"locations":[{"id":"doi:10.21437/interspeech.2004-169","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2015876361","https://openalex.org/W2056457557","https://openalex.org/W2056786202","https://openalex.org/W2137826140","https://openalex.org/W2396921061","https://openalex.org/W3148201686"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W2009254313","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W2015876361","https://openalex.org/W2131486661"],"abstract_inverted_index":{"In":[0,23,123],"[1],":[1],"a":[2,142],"novel":[3],"approach":[4],"is":[5,30],"proposed":[6],"for":[7,55,73],"automatically":[8,32],"segmenting":[9],"and":[10,37,47,61,103,116],"transcribing":[11],"continuous":[12,27],"speech":[13,21,28],"signal":[14,29],"without":[15],"the":[16,26,77,89,95,101,135,151],"use":[17],"of":[18,58,97,105,110,114,120,146,150],"manually":[19],"annotated":[20],"corpora.":[22],"this":[24,124],"approach,":[25],"first":[31],"segmented":[33],"into":[34],"syllable-like":[35],"units":[36],"similar":[38],"syllable":[39,59,68,106,121],"segments":[40,60,99],"are":[41,53,63,70,81,85],"grouped":[42],"together":[43],"using":[44],"an":[45],"unsupervised":[46],"incremental":[48],"clustering":[49,90],"technique.":[50],"Separate":[51],"models":[52,69],"generated":[54],"each":[56],"cluster":[57],"labels":[62],"assigned":[64],"to":[65,93,134],"them.":[66],"These":[67],"then":[71],"used":[72],"recognition/transcription.":[74],"Even":[75],"though":[76],"results":[78],"in":[79,88,141,155],"[1]":[80,156],"quite":[82],"promising,":[83],"there":[84],"some":[86],"problems":[87],"technique":[91],"due":[92],"(i)":[94],"presence":[96],"silence":[98],"at":[100],"beginning":[102],"end":[104],"boundaries.":[107],"(ii)":[108],"fragmentation":[109],"syllables":[111,115],"(iii)":[112],"merging":[113],"(iv)":[117],"poor":[118],"initialization":[119],"models.":[122],"paper":[125],"we":[126],"specifically":[127],"address":[128],"these":[129],"issues,":[130],"make":[131],"several":[132],"refinements":[133],"baseline":[136,152],"system,":[137],"which":[138],"has":[139],"resulted":[140],"significant":[143],"performance":[144],"improvement":[145],"8%":[147],"over":[148],"that":[149],"system":[153],"described":[154]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}