{"id":"https://openalex.org/W2096815491","doi":"https://doi.org/10.21437/interspeech.2013-308","title":"Lightly supervised discriminative training of grapheme models for improved sentence-level alignment of speech and text data","display_name":"Lightly supervised discriminative training of grapheme models for improved sentence-level alignment of speech and text data","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2096815491","doi":"https://doi.org/10.21437/interspeech.2013-308","mag":"2096815491"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-308","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Technical University of Cluj-Napoca, Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["School of Philosophy Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1525","last_page":"1529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9980000257492065,"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/discriminative-model","display_name":"Discriminative model","score":0.8848862648010254},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.8763712644577026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8074263334274292},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7362693548202515},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.662991464138031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6306829452514648},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5871756076812744},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43774157762527466},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4331235885620117},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4254966080188751},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07302707433700562},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0657711923122406}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8848862648010254},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.8763712644577026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8074263334274292},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7362693548202515},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.662991464138031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6306829452514648},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5871756076812744},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43774157762527466},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4331235885620117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4254966080188751},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07302707433700562},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0657711923122406},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2013-308","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/4384307b-5347-4b5c-85dc-77c82b48aa47","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/4384307b-5347-4b5c-85dc-77c82b48aa47","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2533495","https://openalex.org/W34922426","https://openalex.org/W207489108","https://openalex.org/W1245895196","https://openalex.org/W1510837697","https://openalex.org/W1516533146","https://openalex.org/W1517939602","https://openalex.org/W1588593315","https://openalex.org/W1975113979","https://openalex.org/W2001679125","https://openalex.org/W2015687745","https://openalex.org/W2026490135","https://openalex.org/W2034537249","https://openalex.org/W2046058489","https://openalex.org/W2054442733","https://openalex.org/W2063541597","https://openalex.org/W2067117291","https://openalex.org/W2084458093","https://openalex.org/W2105961775","https://openalex.org/W2107457864","https://openalex.org/W2118497033","https://openalex.org/W2129545859","https://openalex.org/W2143577772","https://openalex.org/W2145880678","https://openalex.org/W2250270880","https://openalex.org/W2251812144","https://openalex.org/W2283817422","https://openalex.org/W2294232014","https://openalex.org/W2296111744","https://openalex.org/W2397066715","https://openalex.org/W2406986214","https://openalex.org/W2951143245"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2153058382","https://openalex.org/W2162582511","https://openalex.org/W4245698648","https://openalex.org/W3037446006","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,54,89],"method":[4],"for":[5,21,28,103],"lightly":[6,104],"supervised":[7,105],"discriminative":[8,70,106],"training":[9,24,46,71,107],"using":[10,58],"MMI":[11,69],"to":[12,35,44,77,110],"improve":[13],"the":[14,36,66,73,79,101,111],"alignment":[15],"of":[16,38,68,81,113],"speech":[17],"and":[18,94],"text":[19],"data":[20,84],"use":[22,37,67],"in":[23],"HMM-based":[25],"TTS":[26,32],"systems":[27],"low-resource":[29,55],"languages.":[30],"In":[31,53],"applications,":[33],"due":[34],"long-span":[39],"contexts,":[40],"it":[41],"is":[42],"important":[43],"select":[45],"utterances":[47],"which":[48],"have":[49],"wholly":[50],"correct":[51],"transcriptions.":[52],"setting,":[56],"when":[57],"poorly":[59],"trained":[60],"grapheme":[61,122],"models,":[62,123],"we":[63],"show":[64],"that":[65],"at":[72],"grapheme-level":[74],"enables":[75],"us":[76],"increase":[78],"amount":[80],"correctly":[82],"aligned":[83],"by":[85],"40%,":[86],"while":[87],"maintaining":[88],"7%":[90],"sentence":[91,115],"error":[92,97,116],"rate":[93],"0.8%":[95],"word":[96],"rate.":[98,117],"We":[99],"present":[100],"procedure":[102],"with":[108],"regard":[109],"objective":[112],"minimising":[114],"Index":[118],"Terms:":[119],"automatic":[120],"alignment,":[121],"light":[124],"supervision,":[125],"MMI,":[126],"text-to-speech":[127]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}