{"id":"https://openalex.org/W2143860348","doi":"https://doi.org/10.1109/icassp.2008.4518603","title":"Confidence scores for acoustic model adaptation","display_name":"Confidence scores for acoustic model adaptation","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2143860348","doi":"https://doi.org/10.1109/icassp.2008.4518603","mag":"2143860348"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518603","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5084597617","display_name":"Christian Gollan","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Gollan","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, Computer Science Department 6, RWTH Aachen University, Germany","Computer Science Dept., RWTH Aachen University, Aachen,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department 6, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Computer Science Dept., RWTH Aachen University, Aachen,","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google, Inc., New York, NY, USA","Google Inc., 76 Ninth Avenue 4th Floor New York, 10011, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., 76 Ninth Avenue 4th Floor New York, 10011, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"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":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4289","last_page":"4292"},"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":0.9995999932289124,"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"}},{"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/adaptation","display_name":"Adaptation (eye)","score":0.7325482964515686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6899455189704895},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6075010299682617},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.6052983403205872},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.5652087330818176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45762595534324646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4455045759677887},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42887404561042786},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33770352602005005},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.30742359161376953},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1961231231689453},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08757168054580688},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0862216055393219}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7325482964515686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6899455189704895},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6075010299682617},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.6052983403205872},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.5652087330818176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45762595534324646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4455045759677887},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42887404561042786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33770352602005005},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.30742359161376953},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1961231231689453},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08757168054580688},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0862216055393219},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2008.4518603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518603","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.4501","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.4501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/publications/download/581/Confidence Scores for Acoustic Model Adaptation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.3097","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.3097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/media/research.google.com/en/us/pubs/archive/42647.pdf","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:125806","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/125806","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing : Las Vegas, NV, 31 March - 4 April 2008 / [Institute of Electrical and Electronics Engineers]<br/>IEEE International Conference on Acoustics, Speech and Signal Processing, Las Vegas, NV, USA, 2008-03-31 - 2008-04-04","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W55333121","https://openalex.org/W94829088","https://openalex.org/W106647055","https://openalex.org/W130324013","https://openalex.org/W138260957","https://openalex.org/W1596940414","https://openalex.org/W1823291590","https://openalex.org/W1892722218","https://openalex.org/W2002342963","https://openalex.org/W2100969003","https://openalex.org/W2121981798","https://openalex.org/W2124707525","https://openalex.org/W2146871184","https://openalex.org/W2166810516","https://openalex.org/W2578808052","https://openalex.org/W6603839702","https://openalex.org/W6604245201","https://openalex.org/W6605298800","https://openalex.org/W6605598654","https://openalex.org/W6635521279"],"related_works":["https://openalex.org/W1542224353","https://openalex.org/W1661087619","https://openalex.org/W2116854923","https://openalex.org/W2750730210","https://openalex.org/W2236974868","https://openalex.org/W4312766348","https://openalex.org/W4233939244","https://openalex.org/W2730764323","https://openalex.org/W3123806511","https://openalex.org/W1976727107"],"abstract_inverted_index":{"This":[0,91],"paper":[1],"focuses":[2],"on":[3,112,129],"confidence":[4,13,85],"scores":[5],"for":[6,83],"use":[7,78],"in":[8,17,45,87,100],"acoustic":[9],"model":[10],"adaptation.":[11,25],"Frame-based":[12],"estimates":[14],"are":[15,43,65,89],"used":[16],"linear":[18,40],"transform":[19],"(CMLLR":[20],"and":[21,23,73],"MLLR)":[22],"MAP":[24,64],"We":[26],"show":[27,117],"that":[28,94,101],"adaptation":[29,53,88],"approaches":[30,42,54,82],"with":[31,55,108],"a":[32,56,95,125,130],"limited":[33],"number":[34,58],"of":[35,48,59,70,79,122],"free":[36,60],"parameters":[37,61],"such":[38,62],"as":[39,63],"transform-based":[41],"robust":[44],"the":[46,68,71,104],"face":[47],"frame":[49,105,113],"labeling":[50,106],"errors":[51],"whereas":[52],"large":[57],"sensitive":[66],"to":[67],"quality":[69],"supervision":[72],"hence":[74],"benefit":[75],"most":[76],"from":[77],"confidences.":[80],"Different":[81],"using":[84],"information":[86],"investigated.":[90],"analysis":[92],"shows":[93],"thresholding":[96],"approach":[97],"is":[98],"effective":[99],"it":[102],"improves":[103],"accuracy":[107],"little":[109],"detrimental":[110],"effect":[111],"recall.":[114],"Experimental":[115],"results":[116],"an":[118],"absolute":[119],"WER":[120],"reduction":[121],"2.1%":[123],"over":[124],"CMLLR":[126],"adapted":[127],"system":[128],"video":[131],"transcription":[132],"task.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}