{"id":"https://openalex.org/W1761091820","doi":"https://doi.org/10.21437/interspeech.2005-129","title":"Phoneme alignment based on discriminative learning","display_name":"Phoneme alignment based on discriminative learning","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W1761091820","doi":"https://doi.org/10.21437/interspeech.2005-129","mag":"1761091820"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-129","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 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/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["Hebrew University of Jerusalem ,"],"affiliations":[{"raw_affiliation_string":"Hebrew University of Jerusalem ,","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078263052","display_name":"Shai Shalev\u2010Shwartz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shai Shalev-Shwartz","raw_affiliation_strings":["Alphabet Inc"],"affiliations":[{"raw_affiliation_string":"Alphabet Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113437318","display_name":"Yoram Singer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoram Singer","raw_affiliation_strings":["Alphabet Inc"],"affiliations":[{"raw_affiliation_string":"Alphabet Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103348951","display_name":"Dan Chazan","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Chazan","raw_affiliation_strings":["IBM Research, -"],"affiliations":[{"raw_affiliation_string":"IBM Research, -","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008847407"],"corresponding_institution_ids":["https://openalex.org/I197251160"],"apc_list":null,"apc_paid":null,"fwci":5.4803,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95394918,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2961","last_page":"2964"},"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/discriminative-model","display_name":"Discriminative model","score":0.7872536182403564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.779117226600647},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6475105285644531},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6382803916931152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6211190819740295},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.580646276473999},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.55698561668396},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5344903469085693},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.43845316767692566},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3948196768760681},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26631128787994385}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7872536182403564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779117226600647},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6475105285644531},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6382803916931152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6211190819740295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.580646276473999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.55698561668396},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5344903469085693},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.43845316767692566},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3948196768760681},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26631128787994385}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2005-129","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.918.3097","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.918.3097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Joseph_Keshet/publication/221480950_Phoneme_alignment_based_on_discriminative_learning/links/0deec5332b55a7488b000000.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W77825629","https://openalex.org/W174980304","https://openalex.org/W1560013842","https://openalex.org/W1575243176","https://openalex.org/W1601740268","https://openalex.org/W1832535073","https://openalex.org/W1838096946","https://openalex.org/W1961523962","https://openalex.org/W2054665642","https://openalex.org/W2077804127","https://openalex.org/W2105644991","https://openalex.org/W2109339818","https://openalex.org/W2148603752","https://openalex.org/W2167706101"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W2529301793","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W2098198482"],"abstract_inverted_index":{"We":[0,73,130],"propose":[1],"a":[2,7,11,28,75,96,117,132],"new":[3],"paradigm":[4],"for":[5,104,108,136],"aligning":[6],"phoneme":[8,98],"sequence":[9],"of":[10,59,95],"speech":[12,61,85],"utterance":[13,62],"with":[14,40,64,147],"its":[15,143],"acoustical":[16],"signal":[17],"counterpart.":[18],"In":[19],"contrast":[20],"to":[21,116],"common":[22],"HMM-based":[23],"approaches,":[24],"our":[25,112,153],"method":[26,154],"employs":[27],"discriminative":[29],"learning":[30,35,137],"procedure":[31],"in":[32,119],"which":[33,82,123],"the":[34,41,55,60,65,79,120,138,148,156],"phase":[36],"is":[37,51],"tightly":[38],"coupled":[39],"alignment":[42,47,67,113,139],"task":[43],"at":[44],"hand.":[45],"The":[46],"function":[48,114,140],"we":[49],"devise":[50],"based":[52],"on":[53,101],"mapping":[54,77],"input":[56],"acousticsymbolic":[57],"representations":[58],"along":[63],"target":[66],"into":[68,78],"an":[69],"abstract":[70,80,121],"vector":[71],"space.":[72],"suggest":[74],"specific":[76],"vector-space":[81,122],"utilizes":[83],"standard":[84],"features":[86],"(e.g.":[87],"spectral":[88],"distances)":[89],"as":[90,92],"well":[91],"confidence":[93],"outputs":[94],"framewise":[97],"classifier.":[99],"Building":[100],"techniques":[102],"used":[103],"large":[105],"margin":[106],"methods":[107],"predicting":[109],"whole":[110],"sequences,":[111],"distills":[115],"classifier":[118],"separates":[124],"correct":[125],"alignments":[126],"from":[127],"incorrect":[128],"ones.":[129],"describe":[131],"simple":[133],"iterative":[134],"algorithm":[135],"and":[141],"discuss":[142],"formal":[144],"properties.":[145],"Experiments":[146],"TIMIT":[149],"corpus":[150],"show":[151],"that":[152],"outperforms":[155],"current":[157],"state-of-the-art":[158],"approaches.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}