{"id":"https://openalex.org/W3015823170","doi":"https://doi.org/10.1109/icassp40776.2020.9054066","title":"A Neural Document Language Modeling Framework for Spoken Document Retrieval","display_name":"A Neural Document Language Modeling Framework for Spoken Document Retrieval","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015823170","doi":"https://doi.org/10.1109/icassp40776.2020.9054066","mag":"3015823170"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5076896504","display_name":"Li-Phen Yen","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Li-Phen Yen","raw_affiliation_strings":["National Taiwan University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064729482","display_name":"Zhenyu Wu","orcid":"https://orcid.org/0000-0002-7183-6943"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Zhen-Yu Wu","raw_affiliation_strings":["National Taiwan University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115603153","display_name":"Kuan\u2010Yu Chen","orcid":"https://orcid.org/0000-0002-6036-2199"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Yu Chen","raw_affiliation_strings":["National Taiwan University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076896504"],"corresponding_institution_ids":["https://openalex.org/I154864474"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.03498626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"521","issue":null,"first_page":"8139","last_page":"8143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8727695345878601},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6617496013641357},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6279100179672241},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6235340237617493},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6140539050102234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5965573191642761},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.592947244644165},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.544527530670166},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4813131093978882},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.46714115142822266},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.46692630648612976},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44262075424194336},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3894544839859009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8727695345878601},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6617496013641357},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6279100179672241},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6235340237617493},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6140539050102234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5965573191642761},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.592947244644165},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.544527530670166},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4813131093978882},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.46714115142822266},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.46692630648612976},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44262075424194336},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3894544839859009},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2169610","https://openalex.org/W14941018","https://openalex.org/W210770835","https://openalex.org/W1483313504","https://openalex.org/W1614298861","https://openalex.org/W1880262756","https://openalex.org/W1993692165","https://openalex.org/W2002890640","https://openalex.org/W2030694415","https://openalex.org/W2036315856","https://openalex.org/W2042980227","https://openalex.org/W2046902062","https://openalex.org/W2074767172","https://openalex.org/W2131744502","https://openalex.org/W2134731454","https://openalex.org/W2136189984","https://openalex.org/W2136542423","https://openalex.org/W2148986421","https://openalex.org/W2153252192","https://openalex.org/W2165612380","https://openalex.org/W2169583766","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2642544538","https://openalex.org/W2890045257","https://openalex.org/W2896457183","https://openalex.org/W2919115771","https://openalex.org/W2923890923","https://openalex.org/W2924690340","https://openalex.org/W2938224028","https://openalex.org/W2940118215","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2996428491","https://openalex.org/W2998704965","https://openalex.org/W4240913316","https://openalex.org/W4246962055","https://openalex.org/W4285719527","https://openalex.org/W4385245566","https://openalex.org/W6600089577","https://openalex.org/W6608545824","https://openalex.org/W6636510571","https://openalex.org/W6639619044","https://openalex.org/W6679775712","https://openalex.org/W6680532216","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6760359991","https://openalex.org/W6761268247","https://openalex.org/W6761345506","https://openalex.org/W6763701032","https://openalex.org/W6766673545"],"related_works":["https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3157284875","https://openalex.org/W2147241511","https://openalex.org/W2259406085","https://openalex.org/W3113264705","https://openalex.org/W2099715052","https://openalex.org/W2113651401","https://openalex.org/W4226247999"],"abstract_inverted_index":{"Recent":[0],"developments":[1],"in":[2,11,52,83,108,137],"deep":[3],"learning":[4],"have":[5,48,61,78],"led":[6],"to":[7,42,98,151,196],"a":[8,63,123,156,163,184],"significant":[9],"innovation":[10],"various":[12],"classic":[13],"and":[14,26,139],"practical":[15],"subjects,":[16],"including":[17],"speech":[18,77],"recognition,":[19],"computer":[20],"vision,":[21],"question":[22],"answering,":[23],"information":[24,143],"retrieval":[25,89,125],"so":[27,56],"on.":[28],"In":[29],"the":[30,57,70,81,109,115,118,129,141,146,171,188,192],"context":[31],"of":[32,59,66,72,131,162,178,191],"natural":[33],"language":[34,37,44,133,147,173],"processing":[35],"(NLP),":[36],"representations":[38],"learned":[39,144],"by":[40,145],"referring":[41],"autoregressive":[43],"modeling":[45,134],"or":[46],"autoencoding":[47],"shown":[49],"giant":[50],"successes":[51],"many":[53],"downstream":[54],"tasks,":[55],"school":[58],"studies":[60],"become":[62,103],"major":[64],"stream":[65],"research":[67,106],"recently.":[68],"Because":[69],"immenseness":[71],"multimedia":[73,96],"data":[74],"along":[75],"with":[76,170],"spread":[79],"around":[80],"world":[82],"our":[84,152],"daily":[85],"life,":[86],"spoken":[87],"document":[88],"(SDR),":[90],"which":[91,127],"aims":[92],"at":[93],"retrieving":[94],"relevant":[95],"contents":[97],"satisfy":[99],"users'":[100],"queries,":[101],"has":[102],"an":[104],"important":[105],"subject":[107],"past":[110],"decades.":[111],"Targeting":[112],"on":[113,121,159,183],"enhancing":[114],"SDR":[116,138,166,180],"performance,":[117],"paper":[119],"concentrates":[120],"proposing":[122],"neural":[124,164],"framework,":[126,167,194],"assembles":[128],"merits":[130],"using":[132],"(LM)":[135],"mechanism":[136],"leveraging":[140],"abstractive":[142],"representation":[148,174],"models.":[149],"Consequently,":[150],"knowledge,":[153],"this":[154],"is":[155],"pioneer":[157],"study":[158],"supervised":[160],"training":[161],"LM-based":[165],"especially":[168],"combined":[169],"pretrained":[172],"methods.":[175],"A":[176],"series":[177],"empirical":[179],"experiments":[181],"conducted":[182],"benchmark":[185],"collection":[186],"demonstrate":[187],"good":[189],"efficacy":[190],"proposed":[193],"compared":[195],"several":[197],"existing":[198],"strong":[199],"baseline":[200],"systems.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}