{"id":"https://openalex.org/W2289606411","doi":"https://doi.org/10.1109/asru.2015.7404854","title":"The 2015 sheffield system for transcription of Multi-Genre Broadcast media","display_name":"The 2015 sheffield system for transcription of Multi-Genre Broadcast media","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2289606411","doi":"https://doi.org/10.1109/asru.2015.7404854","mag":"2289606411"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1512.06643","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Oscar Saz","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Oscar Saz","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mortaza Doulaty","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mortaza Doulaty","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Salil Deena","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Salil Deena","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rosanna Milner","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rosanna Milner","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Raymond W. M. Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Raymond W. M. Ng","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Madina Hasan","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Madina Hasan","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yulan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yulan Liu","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":null,"display_name":"Thomas Hain","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":2.6797,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92127533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"624","last_page":"631"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9973000288009644,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9927999973297119,"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/transcription","display_name":"Transcription (linguistics)","score":0.6008999943733215},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5022000074386597},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45010000467300415},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4453999996185303},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.414000004529953},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4133000075817108},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.3578999936580658},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.31859999895095825},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3183000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729200005531311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6434000134468079},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41780000925064087},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.3578999936580658},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3555999994277954},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C58911810","wikidata":"https://www.wikidata.org/wiki/Q273623","display_name":"Radio broadcasting","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2015.7404854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1512.06643","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1512.06643","pdf_url":"https://arxiv.org/pdf/1512.06643","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1512.06643","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1512.06643","pdf_url":"https://arxiv.org/pdf/1512.06643","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1559401186","https://openalex.org/W1904457459","https://openalex.org/W2002342963","https://openalex.org/W2016243284","https://openalex.org/W2037740282","https://openalex.org/W2085598899","https://openalex.org/W2106793713","https://openalex.org/W2107617395","https://openalex.org/W2118497033","https://openalex.org/W2119203697","https://openalex.org/W2128022332","https://openalex.org/W2160815625","https://openalex.org/W2161167754","https://openalex.org/W2161513525","https://openalex.org/W6601546718","https://openalex.org/W6602594759","https://openalex.org/W6607333740","https://openalex.org/W6631036137","https://openalex.org/W6631241246","https://openalex.org/W6631362777","https://openalex.org/W6675912722","https://openalex.org/W6678457041","https://openalex.org/W6680987829","https://openalex.org/W6682641560","https://openalex.org/W6689255713","https://openalex.org/W6712565394","https://openalex.org/W6712868603","https://openalex.org/W6713280142","https://openalex.org/W6713752823","https://openalex.org/W6776783807"],"related_works":[],"abstract_inverted_index":{"We":[0],"describe":[1],"the":[2,10,30,34,38,41,163],"University":[3],"of":[4,17,25,36,40,43,52,75,90,150,160,168],"Sheffield":[5],"system":[6,95,153],"for":[7,54,67],"participation":[8],"in":[9,29,61,83,97],"2015":[11],"Multi-Genre":[12],"Broadcast":[13],"(MGB)":[14],"challenge":[15],"task":[16],"transcribing":[18],"multi-genre":[19,91,170],"broadcast":[20,55,76],"shows.":[21,92,171],"Transcription":[22],"was":[23],"one":[24],"four":[26],"tasks":[27],"proposed":[28],"MGB":[31],"challenge,":[32],"with":[33,69,118,129,143],"aim":[35],"advancing":[37],"state":[39],"art":[42],"automatic":[44,50,72],"speech":[45,73],"recognition,":[46],"speaker":[47,134,146],"diarisation":[48],"and":[49,81,87,137,145],"alignment":[51],"subtitles":[53],"media.":[56],"Four":[57],"topics":[58],"are":[59],"investigated":[60],"this":[62],"work:":[63],"Data":[64],"selection":[65],"techniques":[66],"training":[68],"unreliable":[70],"data,":[71],"segmentation":[74],"media":[77],"shows,":[78],"acoustic":[79],"modelling":[80,89],"adaptation":[82],"highly":[84],"variable":[85],"environments,":[86],"language":[88],"The":[93,148],"final":[94,157],"operates":[96],"multiple":[98],"passes,":[99],"using":[100],"an":[101],"initial":[102],"unadapted":[103],"decoding":[104],"stage":[105,128,142],"to":[106],"refine":[107],"segmentation,":[108],"followed":[109],"by":[110,122,133],"three":[111,152],"adapted":[112],"passes:":[113],"a":[114,139,156],"hybrid":[115,127],"DNN":[116],"pass":[117],"input":[119,130],"features":[120,131],"normalised":[121,132],"speaker-based":[123],"cepstral":[124],"normalisation,":[125],"another":[126],"feature-MLLR":[135],"transformations,":[136],"finally":[138],"bottleneck-based":[140],"tandem":[141],"noise":[144],"factorisation.":[147],"combination":[149],"these":[151],"outputs":[154],"provides":[155],"error":[158],"rate":[159],"27.5%":[161],"on":[162],"official":[164],"development":[165],"set,":[166],"consisting":[167],"47":[169]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}
