{"id":"https://openalex.org/W4392903521","doi":"https://doi.org/10.1109/icassp48485.2024.10446857","title":"Speech Collage: Code-Switched Audio Generation by Collaging Monolingual Corpora","display_name":"Speech Collage: Code-Switched Audio Generation by Collaging Monolingual Corpora","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903521","doi":"https://doi.org/10.1109/icassp48485.2024.10446857"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446857","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/icassp48485.2024.10446857","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014592910","display_name":"Amir Hussein","orcid":"https://orcid.org/0000-0002-0820-4062"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Hussein","raw_affiliation_strings":["Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092964569","display_name":"Dorsa Zeinali","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dorsa Zeinali","raw_affiliation_strings":["Northeastern University, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044666169","display_name":"Ond\u0159ej Klejch","orcid":"https://orcid.org/0000-0001-5495-967X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ond\u0159ej Klejch","raw_affiliation_strings":["University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014455067","display_name":"Matthew Wiesner","orcid":"https://orcid.org/0000-0001-8653-7738"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wiesner","raw_affiliation_strings":["Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021201726","display_name":"Brian Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022279488","display_name":"Shammur Absar Chowdhury","orcid":"https://orcid.org/0000-0002-1331-2543"},"institutions":[],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Shammur Chowdhury","raw_affiliation_strings":["Qatar Computing Research Institute, Doha"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693435","display_name":"Ahmed Ali","orcid":"https://orcid.org/0000-0002-9186-7544"},"institutions":[],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed Ali","raw_affiliation_strings":["Qatar Computing Research Institute, Doha"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institution_assertions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":84},"biblio":{"volume":null,"issue":null,"first_page":"12006","last_page":"12010"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9993,"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/T10860","display_name":"Speech and Audio Processing","score":0.9992,"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/word-error-rate","display_name":"Word error rate","score":0.6511727},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.493626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81765926},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6880801},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6511727},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5276018},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.493626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46435642},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44180822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40518808},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10442078},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446857","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.15674","pdf_url":"http://arxiv.org/pdf/2309.15674","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446857","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":37,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1599623585","https://openalex.org/W197277712","https://openalex.org/W2117686557","https://openalex.org/W2127141656","https://openalex.org/W2416098436","https://openalex.org/W2531638282","https://openalex.org/W2889385306","https://openalex.org/W2891616026","https://openalex.org/W2936842814","https://openalex.org/W2963077089","https://openalex.org/W2963242190","https://openalex.org/W2963250244","https://openalex.org/W2972880214","https://openalex.org/W2972888990","https://openalex.org/W3008480565","https://openalex.org/W3015280134","https://openalex.org/W3015615177","https://openalex.org/W3029522047","https://openalex.org/W3096263335","https://openalex.org/W3097306574","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3155609600","https://openalex.org/W3163135964","https://openalex.org/W3163793923","https://openalex.org/W3196824004","https://openalex.org/W3197295304","https://openalex.org/W3198544738","https://openalex.org/W3217003515","https://openalex.org/W4210811812","https://openalex.org/W4286895682","https://openalex.org/W4287121639","https://openalex.org/W4288408927","https://openalex.org/W4319862717","https://openalex.org/W4372266937","https://openalex.org/W4372269995"],"related_works":["https://openalex.org/W2914603036","https://openalex.org/W2547793174","https://openalex.org/W2544241817","https://openalex.org/W2405439032","https://openalex.org/W2309273277","https://openalex.org/W2158882055","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2061937230","https://openalex.org/W1574295218"],"abstract_inverted_index":{"Designing":[0],"effective":[1],"automatic":[2],"speech":[3,63],"recognition":[4,64],"(ASR)":[5],"systems":[6],"for":[7,96],"Code-Switching":[8],"(CS)":[9],"often":[10],"depends":[11],"on":[12,62],"the":[13,16,45,57,109],"availability":[14],"of":[15,48,59],"transcribed":[17],"CS":[18,33,70,78,106],"resources.":[19],"To":[20],"address":[21],"data":[22,34,61],"scarcity,":[23],"this":[24],"paper":[25],"introduces":[26],"Speech":[27],"Collage,":[28],"a":[29,73],"method":[30],"that":[31,105],"synthesizes":[32],"from":[35],"monolingual":[36,116],"corpora":[37],"by":[38],"splicing":[39],"audio":[40,49],"segments.":[41],"We":[42,55],"further":[43],"improve":[44],"smoothness":[46],"quality":[47],"generation":[50],"using":[51,68],"an":[52],"overlap-add":[53],"approach.":[54],"investigate":[56],"impact":[58],"generated":[60],"in":[65,90],"two":[66],"scenarios:":[67],"in-domain":[69,97],"text":[71],"and":[72,86,93,98,113],"zero-shot":[74,99],"approach":[75],"with":[76],"synthesized":[77],"text.":[79],"Empirical":[80],"results":[81],"highlight":[82],"up":[83],"to":[84],"34.4%":[85],"16.2%":[87],"relative":[88],"reductions":[89],"Mixed-Error":[91],"Rate":[92,95],"Word-Error":[94],"scenarios,":[100],"respectively.":[101],"Lastly,":[102],"we":[103],"demonstrate":[104],"augmentation":[107],"bolsters":[108],"model's":[110],"code-switching":[111],"inclination":[112],"reduces":[114],"its":[115],"bias.":[117]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4392903521","counts_by_year":[],"updated_date":"2024-12-29T21:36:58.438145","created_date":"2024-03-19"}