{"id":"https://openalex.org/W2149295191","doi":"https://doi.org/10.1142/s0219427901000333","title":"Content-based Language Models for Spoken Document Retrieval","display_name":"Content-based Language Models for Spoken Document Retrieval","publication_year":2001,"publication_date":"2001-06-01","ids":{"openalex":"https://openalex.org/W2149295191","doi":"https://doi.org/10.1142/s0219427901000333","mag":"2149295191"},"language":"en","primary_location":{"id":"doi:10.1142/s0219427901000333","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427901000333","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","raw_type":"journal-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/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"HSIN-MIN WANG","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan, ROC"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115595070","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"BERLIN CHEN","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan, ROC"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071214181"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.5272,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78693896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"14","issue":"02","first_page":"193","last_page":"209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9969000220298767,"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":0.8963329792022705},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.695680558681488},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6779831051826477},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6609558463096619},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6395239233970642},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.5941665768623352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5499576330184937},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5376042127609253},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5105277299880981},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46521663665771484},{"id":"https://openalex.org/keywords/clef","display_name":"Clef","score":0.4521905183792114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3429752290248871},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1596435308456421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8963329792022705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.695680558681488},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6779831051826477},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6609558463096619},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6395239233970642},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.5941665768623352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5499576330184937},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5376042127609253},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5105277299880981},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46521663665771484},{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.4521905183792114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3429752290248871},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1596435308456421},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0219427901000333","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427901000333","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W176710706","https://openalex.org/W318278152","https://openalex.org/W1495864251","https://openalex.org/W1546195864","https://openalex.org/W1560013842","https://openalex.org/W1933980377","https://openalex.org/W1998414250","https://openalex.org/W2032459394","https://openalex.org/W2112306108","https://openalex.org/W2157887661","https://openalex.org/W2170217747"],"related_works":["https://openalex.org/W1839123017","https://openalex.org/W107294947","https://openalex.org/W2404292891","https://openalex.org/W4248447766","https://openalex.org/W1510062440","https://openalex.org/W2403658721","https://openalex.org/W1539400004","https://openalex.org/W2101747375","https://openalex.org/W1879326726","https://openalex.org/W2026027976"],"abstract_inverted_index":{"Spoken":[0],"document":[1,38],"retrieval":[2,45],"(SDR)":[3],"has":[4],"been":[5],"extensively":[6],"studied":[7],"in":[8,16,21,101],"recent":[9],"years":[10],"because":[11],"of":[12,31,46,61,73],"its":[13],"potential":[14],"use":[15],"navigating":[17],"large":[18],"multimedia":[19],"collections":[20],"the":[22,52],"near":[23],"future.":[24],"This":[25],"paper":[26],"presents":[27],"a":[28],"novel":[29],"concept":[30],"applying":[32],"content-based":[33,53],"language":[34,54,68],"models":[35,69],"to":[36,78],"spoken":[37,62,74,89],"retrieval.":[39],"In":[40],"an":[41],"example":[42],"task":[43],"for":[44],"Mandarin":[47],"Chinese":[48],"broadcast":[49],"news":[50],"data,":[51],"models,":[55],"either":[56],"trained":[57],"on":[58,96],"automatic":[59,71],"transcriptions":[60,72],"documents":[63,90],"or":[64],"adapted":[65],"from":[66,87],"baseline":[67],"using":[70],"documents,":[75],"were":[76],"used":[77],"create":[79],"more":[80],"accurate":[81],"recognition":[82],"results":[83],"and":[84,91],"indexing":[85],"terms":[86],"both":[88],"speech":[92],"queries.":[93],"We":[94],"report":[95],"some":[97],"interesting":[98],"findings":[99],"obtained":[100],"this":[102],"research.":[103]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
