{"id":"https://openalex.org/W3011871163","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023316","title":"Improving code-switching speech recognition with data augmentation and system combination","display_name":"Improving code-switching speech recognition with data augmentation and system combination","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011871163","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023316","mag":"3011871163"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5066913695","display_name":"Duo Ma","orcid":"https://orcid.org/0000-0001-5453-3652"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Duo Ma","raw_affiliation_strings":["Northwest Minzu University, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101494512","display_name":"Guanyu Li","orcid":"https://orcid.org/0000-0002-9829-6131"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanyu Li","raw_affiliation_strings":["Northwest Minzu University, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"Northwest Minzu University, Lanzhou, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039696635","display_name":"Haihua Xu","orcid":"https://orcid.org/0000-0002-2220-8465"},"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":"Haihua Xu","raw_affiliation_strings":["Temasek Laboratories, Nanyang Technological University, singapore"],"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University, singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","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":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066913695"],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":null,"apc_paid":null,"fwci":0.7001,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79092102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"117","issue":null,"first_page":"1308","last_page":"1312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7856391668319702},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.676302433013916},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6437928676605225},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5087526440620422},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.4741710424423218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36274784803390503},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3350614309310913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7856391668319702},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.676302433013916},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6437928676605225},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5087526440620422},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.4741710424423218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36274784803390503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3350614309310913}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1509793305","https://openalex.org/W1979651826","https://openalex.org/W1989674786","https://openalex.org/W1993721840","https://openalex.org/W2079623482","https://openalex.org/W2097117768","https://openalex.org/W2099621636","https://openalex.org/W2102605133","https://openalex.org/W2111305191","https://openalex.org/W2116236039","https://openalex.org/W2153433699","https://openalex.org/W2163605009","https://openalex.org/W2164240571","https://openalex.org/W2184343439","https://openalex.org/W2219249508","https://openalex.org/W2400997536","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2696967604","https://openalex.org/W2802201485","https://openalex.org/W2883989418","https://openalex.org/W2888867175","https://openalex.org/W2890964092","https://openalex.org/W2964156075","https://openalex.org/W4295727797","https://openalex.org/W6675409298","https://openalex.org/W6684191040","https://openalex.org/W6713346354","https://openalex.org/W6713762819"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036","https://openalex.org/W2124470186"],"abstract_inverted_index":{"We":[0,104],"focused":[1],"on":[2,112,140],"a":[3,80],"study":[4],"of":[5],"comprehensive":[6],"approaches":[7],"to":[8,37,79,85,98,133],"an":[9],"improved":[10],"code-switching":[11,76],"speech":[12,28],"recognition,":[13],"using":[14],"data":[15,22,70,77,86],"augmentation":[16,71,87],"and":[17,51,135,148],"system":[18,154],"combination":[19,96,114],"methods.":[20],"For":[21],"augmentation,":[23],"we":[24,34,60,89,130],"not":[25],"only":[26],"use":[27],"speed":[29],"perturbation":[30],"based":[31,43,54,121],"method,":[32],"but":[33],"also":[35,90],"attempt":[36],"add":[38],"diversified":[39],"room":[40],"impulse":[41],"response":[42],"reverberate":[44],"noise,":[45],"as":[46,48],"well":[47],"music,":[49],"babble,":[50],"white":[52],"noise":[53],"additive":[55],"noise.":[56],"It":[57],"is":[58],"found":[59],"still":[61],"can":[62],"achieve":[63,105,131],"significant":[64,106],"performance":[65],"improvement":[66],"with":[67,125],"such":[68],"noise-corrupted":[69],"methods,":[72,88],"though":[73],"our":[74,101,126],"SEAME":[75],"belongs":[78],"clean":[81],"corpus.":[82],"In":[83],"addition":[84],"adopt":[91],"Minimum":[92],"Bayesian":[93],"risk-based":[94],"lattice":[95,113,122],"method":[97],"further":[99],"improve":[100],"recognition":[102],"results.":[103],"word":[107],"error":[108],"rate":[109],"(WER)":[110],"reduction":[111,139,152],"with/without":[115],"recurrent":[116],"neural":[117],"network":[118],"language":[119],"model":[120],"rescoring.":[123],"Compared":[124],"previous":[127],"efforts":[128],"[6],":[129],"up":[132],"2.29%":[134],"5.61%":[136],"absolute":[137,150],"WER":[138,151],"the":[141],"two":[142],"dev":[143],"sets":[144],"respectively,":[145],"while":[146],"4.83%":[147],"8.04%":[149],"after":[153],"combination.":[155]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}