{"id":"https://openalex.org/W2059861538","doi":"https://doi.org/10.1109/slt.2012.6424219","title":"Improved semantic retrieval of spoken content by language models enhanced with acoustic similarity graph","display_name":"Improved semantic retrieval of spoken content by language models enhanced with acoustic similarity graph","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2059861538","doi":"https://doi.org/10.1109/slt.2012.6424219","mag":"2059861538"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","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/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100547702","display_name":"Tsung-Hsien Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsung-Hsien Wen","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044010123","display_name":"Lin-shan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lin-Shan Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040508737"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":2.5688,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90206536,"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":"182","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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":0.9940999746322632,"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":0.991599977016449,"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":0.8483724594116211},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6441830992698669},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.6157729029655457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5827941298484802},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5317429900169373},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.525114119052887},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5024938583374023},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.501483678817749},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5008518695831299},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4728289544582367},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.457663357257843},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.45188650488853455},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4444802403450012},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4191647171974182},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3636091351509094},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0739034116268158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483724594116211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6441830992698669},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.6157729029655457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827941298484802},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5317429900169373},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.525114119052887},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5024938583374023},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.501483678817749},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5008518695831299},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4728289544582367},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.457663357257843},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.45188650488853455},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4444802403450012},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4191647171974182},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3636091351509094},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0739034116268158},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2012.6424219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W181681892","https://openalex.org/W1612003148","https://openalex.org/W2036223361","https://openalex.org/W2042980227","https://openalex.org/W2052088591","https://openalex.org/W2075722833","https://openalex.org/W2111047231","https://openalex.org/W2116085680","https://openalex.org/W2136542423","https://openalex.org/W2145541974","https://openalex.org/W2148986421","https://openalex.org/W2395613808","https://openalex.org/W2396226914","https://openalex.org/W2403416846","https://openalex.org/W4240913316","https://openalex.org/W6636440780"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W3152143533","https://openalex.org/W3016822073","https://openalex.org/W2626769217","https://openalex.org/W4385572821","https://openalex.org/W2367617289","https://openalex.org/W2321844481"],"abstract_inverted_index":{"Retrieving":[0],"objects":[1],"semantically":[2],"related":[3],"to":[4,38],"the":[5,18,24,31,40,56,69,74,79,92,105],"query":[6,114],"has":[7],"been":[8],"widely":[9],"studied":[10],"in":[11,55,68,77,91],"text":[12],"information":[13],"retrieval.":[14],"However,":[15],"when":[16],"applying":[17],"text-based":[19],"techniques":[20,102],"on":[21,109,126],"spoken":[22,46,66],"content,":[23],"inevitable":[25],"recognition":[26],"errors":[27],"may":[28],"seriously":[29],"degrade":[30],"performance.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"propose":[37],"enhance":[39],"expected":[41,80,85],"term":[42,81,86],"frequencies":[43,87],"estimated":[44],"from":[45],"content":[47],"by":[48],"acoustic":[49,63],"similarity":[50,64],"graphs.":[51],"For":[52],"each":[53],"word":[54],"lexicon,":[57],"a":[58],"graph":[59,75],"is":[60],"constructed":[61],"describing":[62],"among":[65],"segments":[67],"archive.":[70],"Score":[71],"propagation":[72],"over":[73],"helps":[76],"estimating":[78],"frequencies.":[82],"The":[83],"enhanced":[84],"can":[88],"be":[89],"used":[90],"language":[93],"modeling":[94],"retrieval":[95,101],"approach,":[96],"as":[97,99,104],"well":[98],"semantic":[100,111],"such":[103],"document":[106],"expansion":[107,115],"based":[108],"latent":[110,120],"analysis,":[112],"and":[113,119],"considering":[116],"both":[117],"words":[118],"topic":[121],"information.":[122],"Preliminary":[123],"experiments":[124],"performed":[125],"Mandarin":[127],"broadcast":[128],"news":[129],"indicated":[130],"that":[131],"improved":[132],"performance":[133],"were":[134],"achievable":[135],"under":[136],"different":[137],"conditions.":[138]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}