{"id":"https://openalex.org/W2947333546","doi":"https://doi.org/10.21437/interspeech.2019-2533","title":"Lattice-Based Lightly-Supervised Acoustic Model Training","display_name":"Lattice-Based Lightly-Supervised Acoustic Model Training","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2947333546","doi":"https://doi.org/10.21437/interspeech.2019-2533","mag":"2947333546"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2533","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.13150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035806297","display_name":"Joachim Fainberg","orcid":"https://orcid.org/0000-0002-4669-7136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joachim Fainberg","raw_affiliation_strings":["Centre for Speech Technology Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044666169","display_name":"Ond\u0159ej Klejch","orcid":"https://orcid.org/0000-0001-5495-967X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ond\u0159ej Klejch","raw_affiliation_strings":["Institute of Language, Cognition and Computation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Language, Cognition and Computation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steve Renals","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/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"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":"Peter Bell","raw_affiliation_strings":["University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1596","last_page":"1600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7650938034057617},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6983416676521301},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6438411474227905},{"id":"https://openalex.org/keywords/lattice","display_name":"Lattice (music)","score":0.5909340977668762},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5599527955055237},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5142271518707275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5111635327339172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4754970967769623},{"id":"https://openalex.org/keywords/lattice-phase-equaliser","display_name":"Lattice phase equaliser","score":0.4622803032398224},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.44352370500564575},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3922436237335205},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3285641670227051},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2845158278942108},{"id":"https://openalex.org/keywords/adaptive-filter","display_name":"Adaptive filter","score":0.15052613615989685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14678671956062317},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09310644865036011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7650938034057617},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6983416676521301},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6438411474227905},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.5909340977668762},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5599527955055237},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5142271518707275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5111635327339172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4754970967769623},{"id":"https://openalex.org/C111104540","wikidata":"https://www.wikidata.org/wiki/Q1807061","display_name":"Lattice phase equaliser","level":3,"score":0.4622803032398224},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.44352370500564575},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3922436237335205},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3285641670227051},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2845158278942108},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.15052613615989685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14678671956062317},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09310644865036011},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2019-2533","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.13150","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.13150","pdf_url":"https://arxiv.org/pdf/1905.13150","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/0764d11d-892e-47a4-aa01-b43466a06d9e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/0764d11d-892e-47a4-aa01-b43466a06d9e","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fainberg, J, Klejch, O, Renals, S & Bell, P 2019, Lattice-based lightly-supervised acoustic model training. in Proceedings Interspeech 2019. International Speech Communication Association, pp. 1596-1600, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-2533","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/0764d11d-892e-47a4-aa01-b43466a06d9e","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/0764d11d-892e-47a4-aa01-b43466a06d9e","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fainberg, J, Klejch, O, Renals, S & Bell, P 2019, Lattice-based lightly-supervised acoustic model training. in Proceedings Interspeech 2019. International Speech Communication Association, pp. 1596-1600, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-2533","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.1905.13150","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.13150","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2947333546","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.13150","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.13150","pdf_url":"https://arxiv.org/pdf/1905.13150","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1480268964","https://openalex.org/W1517939602","https://openalex.org/W1524333225","https://openalex.org/W1582482241","https://openalex.org/W1586345832","https://openalex.org/W1588593315","https://openalex.org/W1593899244","https://openalex.org/W1904457459","https://openalex.org/W1954397307","https://openalex.org/W1975113979","https://openalex.org/W2033256038","https://openalex.org/W2054442733","https://openalex.org/W2139453310","https://openalex.org/W2140914930","https://openalex.org/W2143577772","https://openalex.org/W2148295152","https://openalex.org/W2151826411","https://openalex.org/W2153687006","https://openalex.org/W2280141299","https://openalex.org/W2288371874","https://openalex.org/W2292656914","https://openalex.org/W2295262519","https://openalex.org/W2407080277","https://openalex.org/W2508020079","https://openalex.org/W2510349098","https://openalex.org/W2514741789","https://openalex.org/W2786234940","https://openalex.org/W2805508463","https://openalex.org/W2888867175","https://openalex.org/W2889347251","https://openalex.org/W2953937146"],"related_works":["https://openalex.org/W2972764791","https://openalex.org/W1480268964","https://openalex.org/W2143577772","https://openalex.org/W2096815491","https://openalex.org/W2404463488","https://openalex.org/W2508020079","https://openalex.org/W2295262519","https://openalex.org/W2981536480","https://openalex.org/W3207595101","https://openalex.org/W2133564850","https://openalex.org/W1562369854","https://openalex.org/W3094965760","https://openalex.org/W3160799772","https://openalex.org/W3025561721","https://openalex.org/W2963747784","https://openalex.org/W2131702393","https://openalex.org/W3015556645","https://openalex.org/W3015356564","https://openalex.org/W2988736778","https://openalex.org/W2798485145"],"abstract_inverted_index":{"In":[0,66],"the":[1,35,52,60,92,107,117,128,133,137],"broadcast":[2,144],"domain":[3],"there":[4],"is":[5,37],"an":[6,40],"abundance":[7],"of":[8],"related":[9],"text":[10,22,33,74],"data":[11,23,53],"and":[12,19,62,135],"partial":[13],"transcriptions,":[14],"such":[15],"as":[16],"closed":[17],"captions":[18],"subtitles.":[20],"This":[21],"can":[24],"be":[25],"used":[26],"for":[27,110],"lightly":[28],"supervised":[29],"training,":[30,112],"in":[31,116],"which":[32],"matching":[34,56,73],"audio":[36],"selected":[38],"using":[39,80],"existing":[41],"speech":[42],"recognition":[43],"model.":[44,84],"Current":[45],"approaches":[46],"to":[47,102],"light":[48],"supervision":[49,90],"typically":[50],"filter":[51],"based":[54],"on":[55,142],"error":[57,130,139],"rates":[58,131],"between":[59],"transcriptions":[61,105],"biased":[63],"decoding":[64],"hypotheses.":[65],"contrast,":[67],"semi-supervised":[68,86,111],"training":[69,87],"does":[70],"not":[71],"require":[72],"data,":[75],"instead":[76],"generating":[77],"a":[78,81,100,143],"hypothesis":[79],"background":[82],"language":[83],"State-of-the-art":[85],"uses":[88],"lattice-based":[89],"with":[91,106],"lattice-free":[93],"MMI":[94],"(LF-MMI)":[95],"objective":[96],"function.":[97],"We":[98,121],"propose":[99],"technique":[101],"combine":[103],"inaccurate":[104],"lattices":[108],"generated":[109],"thus":[113],"preserving":[114],"uncertainty":[115],"lattice":[118],"where":[119],"appropriate.":[120],"demonstrate":[122],"that":[123],"this":[124],"combined":[125],"approach":[126],"reduces":[127,136],"expected":[129],"over":[132],"lattices,":[134],"word":[138],"rate":[140],"(WER)":[141],"task.":[145]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}