{"id":"https://openalex.org/W9453547","doi":"https://doi.org/10.21437/interspeech.2006-139","title":"Vector-based spoken language recognition using output coding","display_name":"Vector-based spoken language recognition using output coding","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W9453547","doi":"https://doi.org/10.21437/interspeech.2006-139","mag":"9453547"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-139","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055221016","display_name":"Rong Tong","orcid":"https://orcid.org/0000-0003-3410-8354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8651,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86461858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"paper 1155","last_page":"Mon2CaP.8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9980999827384949,"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":0.7225866317749023},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6782160401344299},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6353786587715149},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6195236444473267},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6153907775878906},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5354971885681152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5352678298950195},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5344796180725098},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.488326758146286},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.46067413687705994},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4539482593536377},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4156211316585541},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4080791175365448},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16253522038459778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225866317749023},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6782160401344299},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6353786587715149},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6195236444473267},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6153907775878906},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5354971885681152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5352678298950195},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5344796180725098},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.488326758146286},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.46067413687705994},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4539482593536377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4156211316585541},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4080791175365448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16253522038459778},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2006-139","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1564518192","https://openalex.org/W2100546383","https://openalex.org/W2121420451","https://openalex.org/W2149551942","https://openalex.org/W2149684865","https://openalex.org/W2172287020","https://openalex.org/W2799061466"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2320042380","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W2284708545"],"abstract_inverted_index":{"The":[0,101],"vector-based":[1],"spoken":[2,8,65],"language":[3],"recognition":[4],"approach":[5,76,83,108],"converts":[6],"a":[7,11,18,47,58,62],"utterance":[9],"into":[10],"high":[12],"dimensional":[13,49],"vector,":[14,20],"also":[15,68],"known":[16],"as":[17],"bag-of-sounds":[19,35,44],"that":[21,104],"consists":[22],"of":[23,26,64,72],"n-gram":[24],"statistics":[25],"acoustic":[27],"units.":[28],"Dimensionality":[29],"reduction":[30],"would":[31],"better":[32],"prepare":[33],"the":[34,43,70,73,78,90,105],"vectors":[36,45],"for":[37],"classifier":[38],"design.":[39],"We":[40,67],"propose":[41],"projecting":[42],"onto":[46],"low":[48,80],"SVM":[50],"output":[51,74,106],"coding":[52,75,107],"space,":[53],"where":[54],"each":[55],"dimension":[56],"represents":[57],"decision":[59],"hyperplane":[60],"between":[61],"pair":[63],"languages.":[66],"compare":[69],"performances":[71],"and":[77,94],"traditional":[79],"ranking":[81],"approximation":[82],"using":[84],"latent":[85],"semantic":[86],"indexing":[87],"(LSI)":[88],"on":[89],"NIST":[91],"1996,":[92],"2003":[93],"2005":[95],"Language":[96],"Recognition":[97],"Evaluation":[98],"(LRE)":[99],"databases.":[100],"experiments":[102],"show":[103],"consistently":[109],"outperforms":[110],"LSI":[111],"with":[112],"competitive":[113],"results.":[114]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}