{"id":"https://openalex.org/W2187625493","doi":"https://doi.org/10.21437/odyssey.2014-27","title":"Telephone Conversation Speaker Diarization Using Mealy-HMMs","display_name":"Telephone Conversation Speaker Diarization Using Mealy-HMMs","publication_year":2014,"publication_date":"2014-06-16","ids":{"openalex":"https://openalex.org/W2187625493","doi":"https://doi.org/10.21437/odyssey.2014-27","mag":"2187625493"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2014-27","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2014-27","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2014)","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/A5080870411","display_name":"Jean-Fran\u00e7ois Bonastre","orcid":"https://orcid.org/0000-0001-7741-3346"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jean-Fran\u00e7ois Bonastre","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002668439","display_name":"Itshak Lapidot","orcid":"https://orcid.org/0000-0003-1066-3441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Itshak Lapidot","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017529415","display_name":"Samy Bengio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samy Bengio","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080870411"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.409,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75863864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"173","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9815999865531921,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8224112391471863},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.8041151165962219},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7793151140213013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7351409792900085},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.7272455096244812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7146700620651245},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.6464148759841919},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5318108797073364},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5157756805419922},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.491789847612381},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4254961311817169},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3966187536716461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3616648018360138},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26228198409080505},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10527220368385315},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08089664578437805}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8224112391471863},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8041151165962219},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7793151140213013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351409792900085},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.7272455096244812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7146700620651245},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.6464148759841919},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5318108797073364},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5157756805419922},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.491789847612381},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4254961311817169},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3966187536716461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3616648018360138},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26228198409080505},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10527220368385315},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08089664578437805},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2014-27","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2014-27","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2014)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W184144068","https://openalex.org/W1966142845","https://openalex.org/W2001000502","https://openalex.org/W2075773711","https://openalex.org/W2081074144","https://openalex.org/W2099596170","https://openalex.org/W2115599677","https://openalex.org/W2125838338","https://openalex.org/W2131524408","https://openalex.org/W2407275450"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2102309991","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2535886977"],"abstract_inverted_index":{"When":[0],"Hidden":[1],"Markov":[2],"Models":[3],"(HMMs)":[4],"were":[5,12],"first":[6],"introduced,":[7],"two":[8],"competing":[9],"representation":[10],"models":[11],"proposed,":[13],"the":[14,31,41,47,58,70],"Moore":[15,48],"model,":[16,33],"with":[17,34,87],"separate":[18],"emission":[19],"and":[20,30,73,77],"transition":[21],"distributions,":[22],"which":[23],"is":[24],"commonly":[25],"used":[26],"in":[27],"speech":[28],"technologies,":[29],"Mealy":[32],"a":[35,88],"single":[36],"emission-transition":[37],"distribution.":[38],"Since":[39],"then":[40],"literature":[42],"has":[43],"mostly":[44],"focused":[45],"on":[46],"model.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"would":[54],"like":[55],"to":[56,85],"show":[57,78],"use":[59],"of":[60,91],"MealyHMMs":[61],"for":[62,75],"telephone":[63],"conversation":[64],"speaker":[65],"diarization":[66],"task.":[67],"We":[68],"present":[69],"Viterbi":[71],"training":[72],"decoding":[74],"Mealy-HMMs":[76],"that":[79],"it":[80],"yields":[81],"similar":[82],"performance":[83],"compared":[84],"MooreHMMs":[86],"fewer":[89],"number":[90],"parameters.":[92]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}