{"id":"https://openalex.org/W123061250","doi":"https://doi.org/10.21437/eurospeech.2003-397","title":"Automatic segmentation of film dialogues into phonemes and graphemes","display_name":"Automatic segmentation of film dialogues into phonemes and graphemes","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W123061250","doi":"https://doi.org/10.21437/eurospeech.2003-397","mag":"123061250"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-397","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5079352923","display_name":"Gilles Boulianne","orcid":"https://orcid.org/0000-0001-9383-6189"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gilles Boulianne","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113705695","display_name":"Jean\u2010Fran\u00e7ois Beaumont","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Francois Beaumont","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051056084","display_name":"Patrick Cardinal","orcid":"https://orcid.org/0009-0000-9439-9910"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Cardinal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016610146","display_name":"Michel Comeau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michel Comeau","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061517549","display_name":"Pierre Ouellet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Ouellet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034083532","display_name":"Pierre Dumouchel","orcid":"https://orcid.org/0000-0001-5584-4428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Dumouchel","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5079352923"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01431096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1241","last_page":"1244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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/T12031","display_name":"Speech and dialogue systems","score":0.9900000095367432,"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":0.7957613468170166},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7338625192642212},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6997629404067993},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6803012490272522},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6518084406852722},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6206714510917664},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.585663378238678},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5449941158294678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4812628924846649},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4669519364833832},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46610885858535767},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41975340247154236},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32924050092697144},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.162397563457489},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08343639969825745},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0655616819858551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957613468170166},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7338625192642212},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6997629404067993},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6803012490272522},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6518084406852722},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6206714510917664},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.585663378238678},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5449941158294678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4812628924846649},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4669519364833832},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46610885858535767},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41975340247154236},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32924050092697144},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.162397563457489},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08343639969825745},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0655616819858551},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-397","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.3397","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.3397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.crim.ca/Publications/2003/Documents/pleinTexte/PAR_BouGals_Eurosp03.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1654022110","https://openalex.org/W2040102554","https://openalex.org/W2285729352"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"In":[0],"film":[1,63,75,114,163],"post-production,":[2],"efficient":[3],"methods":[4],"for":[5,165],"re-recording":[6],"a":[7,12,16,37,54,119,166,175],"dialogue":[8],"or":[9,89],"dubbing":[10],"in":[11,36,65,77],"new":[13],"language":[14],"require":[15],"precisely":[17],"time-aligned":[18,167],"text,":[19,168],"with":[20],"individual":[21],"letters":[22],"time-coded":[23],"to":[24,79,148,173],"video":[25],"frame":[26],"resolution.":[27],"Currently,":[28],"this":[29,44],"time":[30],"alignment":[31,146],"is":[32],"performed":[33],"by":[34],"experts":[35],"painstaking":[38],"and":[39,57,67,128,156,169],"slow":[40],"process.":[41,182],"To":[42],"automate":[43,174],"process,":[45],"we":[46],"used":[47],"CRIM\u2019s":[48],"largevocabulary":[49],"HMM":[50,153],"speech":[51,101],"recognizer":[52],"as":[53,86],"phoneme":[55,110,154],"segmenter":[56,97],"measured":[58],"its":[59],"accuracy":[60],"on":[61,99,112],"typical":[62,113],"extracts":[64],"French":[66],"English.":[68],"Our":[69],"results":[70],"reveal":[71],"several":[72],"characteristics":[73],"of":[74,130,162,178],"dialogues,":[76],"addition":[78],"noise,":[80],"that":[81],"affect":[82],"segmentation":[83,155],"accuracy,":[84],"such":[85],"speaking":[87],"style":[88],"reverberant":[90],"recordings.":[91],"Despite":[92],"these":[93],"difficulties,":[94],"an":[95,143,149],"HMM-based":[96],"trained":[98],"clean":[100],"can":[102],"still":[103],"provide":[104],"more":[105],"than":[106],"89":[107],"%":[108],"acceptable":[109],"boundaries":[111],"extracts.":[115],"We":[116],"also":[117],"propose":[118],"method":[120,134],"which":[121],"provides":[122],"the":[123,131,160,179],"correspondence":[124,158],"between":[125],"aligned":[126],"phonemes":[127],"graphemes":[129],"text.":[132],"The":[133],"does":[135],"not":[136],"use":[137],"explicit":[138],"rules,":[139],"but":[140],"rather":[141],"computes":[142],"optimal":[144],"string":[145],"according":[147],"edit-distance":[150],"metric.":[151],"Together,":[152],"phonemegrapheme":[157],"meet":[159],"needs":[161],"postproduction":[164],"make":[170],"it":[171],"possible":[172],"large":[176],"part":[177],"current":[180],"post-synch":[181],"1.":[183]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}