{"id":"https://openalex.org/W2163314930","doi":"https://doi.org/10.21437/interspeech.2007-510","title":"Detection-based ASR in the automatic speech attribute transcription project","display_name":"Detection-based ASR in the automatic speech attribute transcription project","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W2163314930","doi":"https://doi.org/10.21437/interspeech.2007-510","mag":"2163314930"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-510","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5066661740","display_name":"Ilana Bromberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ilana Bromberg","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103865471","display_name":"Qian Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Qian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603082","display_name":"Jun Hou","orcid":"https://orcid.org/0000-0001-9437-4035"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Hou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102725787","display_name":"Chengyuan Ma","orcid":"https://orcid.org/0000-0001-5126-5883"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengyuan Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034852758","display_name":"Brett Matthews","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brett Matthews","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072051550","display_name":"A. Moreno-Daniel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio Moreno-Daniel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053751144","display_name":"Jeremy Morris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeremy Morris","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445125","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-9500-081X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5066661740"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7615,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96646694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1829","last_page":"1832"},"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":0.9976000189781189,"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":0.994700014591217,"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/crfs","display_name":"CRFS","score":0.9396906495094299},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.8240792751312256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8208431005477905},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.792858898639679},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6761272549629211},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.6531221270561218},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5850330591201782},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5675345063209534},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4914175271987915},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.47793295979499817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47532418370246887},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.41718360781669617},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.41596418619155884},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34912240505218506},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3393459916114807},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23768892884254456}],"concepts":[{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.9396906495094299},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8240792751312256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8208431005477905},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.792858898639679},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6761272549629211},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.6531221270561218},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5850330591201782},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5675345063209534},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4914175271987915},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.47793295979499817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47532418370246887},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.41718360781669617},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.41596418619155884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34912240505218506},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393459916114807},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23768892884254456},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2007-510","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/649499","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/649499","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","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":null,"raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W106393560","https://openalex.org/W110305337","https://openalex.org/W116478402","https://openalex.org/W155708904","https://openalex.org/W180740594","https://openalex.org/W188247790","https://openalex.org/W202359724","https://openalex.org/W1490506669","https://openalex.org/W1598851216","https://openalex.org/W1985836220","https://openalex.org/W2117671523","https://openalex.org/W2119155265","https://openalex.org/W2136389896","https://openalex.org/W2168331946","https://openalex.org/W2949468472"],"related_works":["https://openalex.org/W50079190","https://openalex.org/W2356597680","https://openalex.org/W182104056","https://openalex.org/W2111726165","https://openalex.org/W2011251309","https://openalex.org/W3108423214","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W2511246383","https://openalex.org/W2184553228"],"abstract_inverted_index":{"We":[0,67,90],"present":[1],"methods":[2,53,60],"of":[3,18,26,54,61,86,99,122,134],"detector":[4],"design":[5],"in":[6,38,139],"the":[7,16,44,112,125,135,140],"Automatic":[8],"Speech":[9],"Attribute":[10],"Transcription":[11],"project.":[12],"This":[13],"paper":[14,40,141],"details":[15],"results":[17],"a":[19,119],"student-led,":[20],"cross-site":[21],"collaboration":[22],"between":[23],"Georgia":[24],"Institute":[25],"Technology,":[27],"The":[28,35],"Ohio":[29],"State":[30],"University":[31],"and":[32,42,48,59,74,96,127],"Rutgers":[33],"University.":[34],"work":[36],"reported":[37],"this":[39],"describes":[41],"evaluates":[43],"detection-based":[45],"ASR":[46],"paradigm":[47],"discusses":[49],"phonetic":[50,57,87],"attribute":[51,63,88,136],"classes,":[52],"detecting":[55],"framewise":[56,104],"attributes":[58],"combining":[62],"detectors":[64,137],"for":[65,82,107],"ASR.":[66],"use":[68,91],"Multi-Layer":[69],"Perceptrons,":[70],"Hidden":[71],"Markov":[72],"Models":[73],"Support":[75],"Vector":[76],"Machines":[77],"to":[78,102],"compute":[79],"confidence":[80],"scores":[81,106],"several":[83],"prescribed":[84],"sets":[85],"classes.":[89],"Conditional":[92],"Random":[93],"Fields":[94],"(CRFs)":[95],"knowledge-based":[97],"rescoring":[98],"phone":[100,109,120],"lattices":[101],"combine":[103],"detection":[105],"continuous":[108],"recognition":[110],"on":[111],"TIMIT":[113],"database.":[114],"With":[115],"CRFs,":[116],"we":[117],"achieve":[118],"accuracy":[121],"70.63%,":[123],"outperforming":[124],"baseline":[126],"enhanced":[128],"HMM":[129],"systems,":[130],"by":[131],"incorporating":[132],"all":[133],"discussed":[138]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}