{"id":"https://openalex.org/W4239868194","doi":"https://doi.org/10.21437/interspeech.2010-277","title":"Dialect recognition using a phone-GMM-supervector-based SVM kernel","display_name":"Dialect recognition using a phone-GMM-supervector-based SVM kernel","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W4239868194","doi":"https://doi.org/10.21437/interspeech.2010-277"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-277","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5055592425","display_name":"Fadi Biadsy","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fadi Biadsy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045037642","display_name":"Julia Hirschberg","orcid":"https://orcid.org/0000-0003-0689-7616"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julia Hirschberg","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074839699","display_name":"Michael J. Collins","orcid":"https://orcid.org/0000-0001-5226-5498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Collins","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055592425"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8619,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88766959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"753","last_page":"756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9473999738693237,"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":0.9473999738693237,"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/support-vector-machine","display_name":"Support vector machine","score":0.7706372737884521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7111196517944336},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6546502709388733},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5149584412574768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5018095970153809},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49316805601119995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4553757607936859},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1523112952709198},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.046511173248291016}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7706372737884521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111196517944336},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6546502709388733},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5149584412574768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5018095970153809},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49316805601119995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4553757607936859},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1523112952709198},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.046511173248291016},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-277","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.8934","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.8934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.columbia.edu/speech/PaperFiles/2010/biadsy_etal2010_IS10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W2012353789","https://openalex.org/W2530420969","https://openalex.org/W2051187167","https://openalex.org/W2061937230"],"abstract_inverted_index":{"In":[0],"this":[1,69],"paper,":[2],"we":[3,28,52,92],"introduce":[4],"a":[5,25,37,54,117],"new":[6],"approach":[7,84],"to":[8,71,96],"dialect":[9],"recognition":[10],"which":[11,107],"relies":[12],"on":[13,85],"the":[14,31,59,132],"hypothesis":[15],"that":[16,57,75],"certain":[17],"phones":[18,62],"are":[19],"realized":[20],"differently":[21],"across":[22],"dialects.":[23],"Given":[24],"speaker\u2019s":[26],"utterance,":[27],"first":[29],"obtain":[30],"most":[32],"likely":[33],"phone":[34,38,47],"sequence":[35],"using":[36],"recognizer.":[39],"We":[40,67],"then":[41],"extract":[42],"GMM":[43],"Supervectors":[44],"for":[45],"each":[46],"instance.":[48],"Using":[49],"these":[50,129],"vectors,":[51],"design":[53],"kernel":[55,70],"function":[56],"computes":[58],"similarities":[60],"of":[61,65,105,135],"between":[63],"pairs":[64],"utterances.":[66],"employ":[68],"train":[72],"SVM":[73],"classifiers":[74],"estimate":[76],"posterior":[77],"probabilities,":[78],"used":[79],"during":[80],"recognition.":[81],"Testing":[82],"our":[83,94,101,111,136],"four":[86],"Arabic":[87],"dialects":[88],"from":[89],"30s":[90],"cuts,":[91],"compare":[93],"performance":[95],"five":[97],"approaches:":[98],"PRLM;":[99],"GMM-UBM;":[100],"own":[102],"improved":[103],"version":[104],"GMM-UBM":[106,121],"employs":[108],"fMLLR":[109],"adaptation;":[110],"recent":[112],"discriminative":[113],"phonotactic":[114],"approach;":[115],"and":[116],"state-of-the-art":[118],"system:":[119],"SDC-based":[120],"discriminatively":[122],"trained.":[123],"Our":[124],"kernel-based":[125],"technique":[126],"outperforms":[127],"all":[128],"previous":[130],"approaches;":[131],"overall":[133],"EER":[134],"system":[137],"is":[138],"4.9%.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}