{"id":"https://openalex.org/W2049032416","doi":"https://doi.org/10.1109/icassp.2013.6639083","title":"Language diarization for code-switch conversational speech","display_name":"Language diarization for code-switch conversational speech","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2049032416","doi":"https://doi.org/10.1109/icassp.2013.6639083","mag":"2049032416"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5002032106","display_name":"Dau-Cheng Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Dau-Cheng Lyu","raw_affiliation_strings":["Temasek Laboratories, Nanyang Technological University, Singapore","Temasek Labs., Nanyang Technol. Univ., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Temasek Labs., Nanyang Technol. Univ., Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng-Siong Chng","raw_affiliation_strings":["Temasek Laboratories, School of Computer Engineering, Nanyang Technological University, Singapore","Temasek Labs., Nanyang Technol. Univ., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Temasek Labs., Nanyang Technol. Univ., Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"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/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore, SG","Temasek Labs., Nanyang Technol. Univ., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Temasek Labs., Nanyang Technol. Univ., Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002032106"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.8855,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.91460752,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7314","last_page":"7318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9980000257492065,"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":0.9975000023841858,"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":0.8298323154449463},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.820183515548706},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8148798942565918},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7326880097389221},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5967516899108887},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5218971371650696},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5108294486999512},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49590763449668884},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.480984091758728},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47278547286987305},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4699666202068329},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4399903118610382},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4293842911720276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3882037103176117},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.24294176697731018},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18884232640266418},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08832469582557678},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.08763635158538818},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07176417112350464},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0632583498954773}],"concepts":[{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.8298323154449463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820183515548706},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8148798942565918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7326880097389221},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5967516899108887},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5218971371650696},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5108294486999512},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49590763449668884},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.480984091758728},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47278547286987305},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4699666202068329},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4399903118610382},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4293842911720276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3882037103176117},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.24294176697731018},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18884232640266418},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08832469582557678},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.08763635158538818},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07176417112350464},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0632583498954773},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W1583636673","https://openalex.org/W1983072039","https://openalex.org/W2081074144","https://openalex.org/W2091409162","https://openalex.org/W2104457544","https://openalex.org/W2106284094","https://openalex.org/W2114569717","https://openalex.org/W2147880316","https://openalex.org/W2161490380","https://openalex.org/W2172287020","https://openalex.org/W6682082992"],"related_works":["https://openalex.org/W1602082497","https://openalex.org/W2118180989","https://openalex.org/W2975191379","https://openalex.org/W2061937230","https://openalex.org/W2003136674","https://openalex.org/W1556857061","https://openalex.org/W2177420620","https://openalex.org/W4296594783","https://openalex.org/W4387225169","https://openalex.org/W4380994539"],"abstract_inverted_index":{"This":[0],"paper":[1],"examines":[2],"the":[3,8,44,83,113,122],"process":[4,9,63],"of":[5,85,96,128,140,149],"language":[6,12,46,57,70,99,114],"diarization,":[7],"to":[10,151,155,159,164],"perform":[11],"segmentation":[13],"and":[14,43,82,87,144,162],"recognition,":[15],"in":[16],"a":[17,26,69,92,103,134],"code-switched":[18],"speech.":[19],"Towards":[20],"this":[21],"task,":[22],"we":[23,67,111,132],"have":[24],"developed":[25],"63":[27],"hours":[28],"conversational":[29],"code-switch":[30,105,123],"corpus":[31,124],"recorded":[32],"from":[33,121],"Singapore/Malaysia":[34],"speakers.":[35],"We":[36,90],"show":[37],"that":[38],"code-switching":[39],"can":[40],"occur":[41],"frequently":[42],"average":[45],"interval":[47],"may":[48],"be":[49],"as":[50,52],"short":[51,65],"one":[53],"second.":[54],"As":[55],"such,":[56],"diarization":[58,71,100],"is":[59],"challenging":[60],"task.":[61],"To":[62,107],"such":[64],"segments,":[66],"propose":[68],"system":[72],"using":[73],"long":[74],"term":[75],"context":[76],"feature":[77],"across":[78],"several":[79],"phone-based":[80],"segments":[81,119],"combination":[84],"acoustics":[86],"phonotactic":[88],"information.":[89],"achieved":[91],"frame":[93],"error":[94,137],"rate":[95,138],"14.7%":[97],"for":[98],"performance":[101,116],"on":[102,117,146],"Mandarin-English":[104],"corpus.":[106],"evaluate":[108],"our":[109],"system,":[110],"measured":[112],"recognition":[115],"monolingual":[118],"extracted":[120],"against":[125],"published":[126],"techniques":[127],"LID":[129],"systems":[130],"-":[131],"obtained":[133],"relative":[135],"equal":[136],"reduction":[139],"5.2%,":[141],"13.8%,":[142],"15.1%":[143],"17.9%":[145],"speech":[147],"durations":[148],"0.1":[150],"0.5":[152,154],"sec.,":[153,157],"1":[156,158],"3":[160,163],"sec.":[161],"9":[165],"sec":[166],"respectively.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
