{"id":"https://openalex.org/W1974698773","doi":"https://doi.org/10.1145/1076034.1076098","title":"A phonotactic-semantic paradigm for automatic spoken document classification","display_name":"A phonotactic-semantic paradigm for automatic spoken document classification","publication_year":2005,"publication_date":"2005-08-15","ids":{"openalex":"https://openalex.org/W1974698773","doi":"https://doi.org/10.1145/1076034.1076098","mag":"1974698773"},"language":"en","primary_location":{"id":"doi:10.1145/1076034.1076098","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Institute for Infocomm Research, Keng Terrace, Singapore","Institute for Infocomm Research, Keng Terrace, Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Keng Terrace, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research, Keng Terrace, Singapore#TAB#","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research, Keng Terrace, Singapore","Institute for Infocomm Research, Keng Terrace, Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Keng Terrace, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research, Keng Terrace, Singapore#TAB#","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100749735"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":2.2698,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87836815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/phonotactics","display_name":"Phonotactics","score":0.8438223600387573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8390099406242371},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6895055174827576},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6755058765411377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6630351543426514},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5576844215393066},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5112104415893555},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4757687449455261},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4615497589111328},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4554729759693146},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.44567418098449707},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18329036235809326},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.08788982033729553}],"concepts":[{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.8438223600387573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8390099406242371},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6895055174827576},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6755058765411377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6630351543426514},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5576844215393066},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5112104415893555},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4757687449455261},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4615497589111328},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4554729759693146},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.44567418098449707},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18329036235809326},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.08788982033729553},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1076034.1076098","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.1155","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.1155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www1.i2r.a-star.edu.sg/~hli/papers/SIGIR05_p369-ma.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"},{"id":"https://openalex.org/F4320334744","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W12823375","https://openalex.org/W73128518","https://openalex.org/W176773998","https://openalex.org/W210770835","https://openalex.org/W1533946607","https://openalex.org/W1676280465","https://openalex.org/W2045801524","https://openalex.org/W2063337876","https://openalex.org/W2084134149","https://openalex.org/W2095501777","https://openalex.org/W2108995755","https://openalex.org/W2117520332","https://openalex.org/W2118714763","https://openalex.org/W2140390894","https://openalex.org/W2168119002","https://openalex.org/W2172287020","https://openalex.org/W3017143921","https://openalex.org/W4241850027","https://openalex.org/W4285719527","https://openalex.org/W6638242872","https://openalex.org/W6776565550"],"related_works":["https://openalex.org/W2615317726","https://openalex.org/W2021909761","https://openalex.org/W198649858","https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2467354670","https://openalex.org/W2498910126","https://openalex.org/W2133733652","https://openalex.org/W2497306275","https://openalex.org/W166909741"],"abstract_inverted_index":{"We":[0,85],"demonstrate":[1],"a":[2,14,49,53,57,64,71,75,80,108],"phonotactic-semantic":[3,88,105],"paradigm":[4,110],"for":[5,32],"spoken":[6,28,54,65,81,112,122],"document":[7,55,59,66,113],"categorization.":[8],"In":[9],"this":[10],"framework,":[11],"we":[12],"define":[13],"set":[15],"of":[16,20,60],"acoustic":[17,25,33,47,61],"words":[18,22],"instead":[19],"lexical":[21],"to":[23],"represent":[24],"activities":[26],"in":[27,111,120],"languages.":[29],"The":[30,104],"strategy":[31],"vocabulary":[34],"selection":[35,42],"is":[36],"studied":[37],"by":[38,70,117],"comparing":[39],"different":[40],"feature":[41],"methods.":[43],"With":[44],"an":[45],"appropriate":[46],"vocabulary,":[48],"voice":[50],"tokenizer":[51],"converts":[52],"into":[56],"text-like":[58],"words.":[62],"Thus,":[63],"can":[67],"be":[68],"represented":[69],"count":[72],"vector,":[73,77],"named":[74],"bag-of-sounds":[76],"which":[78],"characterizes":[79],"document's":[82],"semantic":[83,98],"domain.":[84],"study":[86],"two":[87],"classifiers,":[89],"the":[90,96,121,136],"support":[91],"vector":[92],"machine":[93],"classifier":[94],"and":[95,101],"latent":[97],"analysis":[99],"classifier,":[100],"their":[102],"properties.":[103],"framework":[106],"constitutes":[107],"new":[109],"classification,":[114],"as":[115],"demonstrated":[116],"its":[118],"success":[119],"language":[123],"identification":[124],"task.":[125],"It":[126],"achieves":[127],"18.2%":[128],"error":[129],"reduction":[130],"over":[131],"state-of-the-art":[132],"benchmark":[133],"performance":[134],"on":[135],"1996":[137],"NIST":[138],"Language":[139],"Recognition":[140],"Evaluation":[141],"database.":[142]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}