{"id":"https://openalex.org/W2401273849","doi":"https://doi.org/10.1109/icassp.2016.7472769","title":"Improved DNN-based segmentation for multi-genre broadcast audio","display_name":"Improved DNN-based segmentation for multi-genre broadcast audio","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2401273849","doi":"https://doi.org/10.1109/icassp.2016.7472769","mag":"2401273849"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5016797233","display_name":"L. Wang","orcid":"https://orcid.org/0000-0002-5189-7562"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"L. Wang","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007989522","display_name":"C. Zhang","orcid":"https://orcid.org/0000-0002-2173-6872"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"C. Zhang","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. C. Woodland","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M. J. F. Gales","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006537074","display_name":"Penny Karanasou","orcid":"https://orcid.org/0000-0003-1939-4161"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. Karanasou","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003588321","display_name":"Pierre Lanchantin","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. Lanchantin","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029689557","display_name":"Xiaobing Liu","orcid":"https://orcid.org/0000-0003-1142-5816"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"X. Liu","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Y. Qian","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5016797233"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":2.8003,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91304857,"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":"5700","last_page":"5704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8035804033279419},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7215058207511902},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6886142492294312},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5591785907745361},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5351909399032593},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5242909789085388},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4678528904914856},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44332388043403625},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39000701904296875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38851356506347656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8035804033279419},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7215058207511902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6886142492294312},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5591785907745361},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5351909399032593},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5242909789085388},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4678528904914856},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44332388043403625},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39000701904296875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38851356506347656},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:771679","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/771679/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W3765491","https://openalex.org/W15516501","https://openalex.org/W106647055","https://openalex.org/W115846232","https://openalex.org/W1547083988","https://openalex.org/W1589339348","https://openalex.org/W1985242443","https://openalex.org/W1999454387","https://openalex.org/W2048497537","https://openalex.org/W2074394031","https://openalex.org/W2081074144","https://openalex.org/W2085066665","https://openalex.org/W2123550723","https://openalex.org/W2130426352","https://openalex.org/W2138029428","https://openalex.org/W2143577772","https://openalex.org/W2147768505","https://openalex.org/W2158146178","https://openalex.org/W2159591770","https://openalex.org/W2160815625","https://openalex.org/W2161513525","https://openalex.org/W2184045248","https://openalex.org/W2288402171","https://openalex.org/W2289874485","https://openalex.org/W2290892587","https://openalex.org/W2292479959","https://openalex.org/W2294745040","https://openalex.org/W2395271510","https://openalex.org/W2396495723","https://openalex.org/W2406262283","https://openalex.org/W2407698769","https://openalex.org/W6600154122","https://openalex.org/W6600640353","https://openalex.org/W6604245201","https://openalex.org/W6604730075","https://openalex.org/W6632910081","https://openalex.org/W6635144179","https://openalex.org/W6646535293","https://openalex.org/W6697247452","https://openalex.org/W6712515972","https://openalex.org/W6712635302","https://openalex.org/W6713606482","https://openalex.org/W6713752823"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W151018310","https://openalex.org/W2620660273","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W4385611764","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Automatic":[0],"segmentation":[1,42],"is":[2,15,64],"a":[3,22,41,81,86],"crucial":[4],"initial":[5],"processing":[6,9],"step":[7],"for":[8,44,118],"multi-genre":[10,45],"broadcast":[11,46],"(MGB)":[12],"audio.":[13,37,92],"It":[14],"very":[16],"challenging":[17],"since":[18],"the":[19,96,102,113,119],"data":[20],"exhibits":[21],"wide":[23],"range":[24],"of":[25,35,59,83,89],"both":[26],"speech":[27],"types":[28,34],"and":[29,62,76],"background":[30],"conditions":[31],"with":[32,48,80],"many":[33],"non-speech":[36],"This":[38],"paper":[39],"describes":[40],"system":[43],"audio":[47],"deep":[49],"neural":[50],"network":[51],"(DNN)":[52],"based":[53],"speech/non-speech":[54],"detection.":[55],"A":[56],"further":[57],"stage":[58],"change-point":[60],"detection":[61],"clustering":[63],"used":[65],"to":[66,112],"obtain":[67],"homogeneous":[68],"segments.":[69],"Suitable":[70],"DNN":[71,115],"inputs,":[72],"context":[73],"window":[74],"sizes":[75],"architectures":[77],"are":[78],"studied":[79],"series":[82],"experiments":[84],"using":[85],"large":[87],"corpus":[88],"MGB":[90,94,122],"television":[91],"For":[93],"transcription,":[95],"improved":[97],"segmenter":[98,116],"yields":[99],"roughly":[100],"half":[101],"increase":[103],"in":[104],"word":[105],"error":[106],"rate,":[107],"over":[108],"manual":[109],"segmentation,":[110],"compared":[111],"baseline":[114],"supplied":[117],"2015":[120],"ASRU":[121],"challenge.":[123]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}