{"id":"https://openalex.org/W4319780044","doi":"https://doi.org/10.1109/iscslp57327.2022.10037962","title":"The NPU-ASLP System for The ISCSLP 2022 Magichub Code-Swiching ASR Challenge","display_name":"The NPU-ASLP System for The ISCSLP 2022 Magichub Code-Swiching ASR Challenge","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319780044","doi":"https://doi.org/10.1109/iscslp57327.2022.10037962"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037962","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10037962","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102543677","display_name":"Yuhao Liang","orcid":"https://orcid.org/0009-0008-9516-6594"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Liang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085355820","display_name":"Peikun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peikun Chen","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085413616","display_name":"Tianyi Xu","orcid":"https://orcid.org/0009-0001-5332-8881"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Xu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068298033","display_name":"Yingying Gao","orcid":"https://orcid.org/0000-0002-6869-3013"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Gao","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China","China Mobile Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"532","last_page":"536"},"is_retracted":false,"is_paratext":false,"is_xpac":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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8338525295257568},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6769261360168457},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6289606094360352},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5424594879150391},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5021812915802002},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4835233688354492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4589155614376068},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45780086517333984},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4147680401802063},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41291365027427673},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4112902879714966},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.40421757102012634},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3768441379070282},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24366667866706848},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14645856618881226},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.11913815140724182}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8338525295257568},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6769261360168457},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6289606094360352},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5424594879150391},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5021812915802002},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4835233688354492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4589155614376068},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45780086517333984},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4147680401802063},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41291365027427673},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4112902879714966},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.40421757102012634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3768441379070282},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24366667866706848},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14645856618881226},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.11913815140724182},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037962","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10037962","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1904457459","https://openalex.org/W2899685446","https://openalex.org/W2962780374","https://openalex.org/W2964156075","https://openalex.org/W2972625221","https://openalex.org/W3096122506","https://openalex.org/W3133595249","https://openalex.org/W3147984406","https://openalex.org/W3163135964","https://openalex.org/W3165404421","https://openalex.org/W3196950043","https://openalex.org/W3197478142","https://openalex.org/W3208049241","https://openalex.org/W4221167707","https://openalex.org/W4224925136","https://openalex.org/W4224939570","https://openalex.org/W4225272718","https://openalex.org/W4225304491","https://openalex.org/W4281770669","https://openalex.org/W4283707580","https://openalex.org/W4285070019","https://openalex.org/W4297841547","https://openalex.org/W4395957972","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6750489868","https://openalex.org/W6780815891","https://openalex.org/W6783867762","https://openalex.org/W6800319369","https://openalex.org/W6803425590","https://openalex.org/W6839144119"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,42],"NPU-ASLP":[4],"system":[5,108],"submitted":[6,107],"to":[7,96,122],"the":[8,50,57,63,68,117,123,127],"ISCSLP":[9],"2022":[10],"Magichub":[11],"Code-Switching":[12],"ASR":[13,25],"Challenge.":[14],"In":[15],"this":[16],"challenge,":[17,69],"we":[18,47,70,91],"first":[19],"explore":[20,92],"several":[21],"popular":[22],"end-to-end":[23],"multilingual":[24],"architectures":[26],"and":[27,35,84,120],"training":[28,65],"strategies,":[29,75],"including":[30,76],"bi-encoder,":[31],"language-aware":[32],"encoder":[33],"(LAE)":[34],"mixture":[36],"of":[37,100],"experts":[38],"(MoE).":[39],"To":[40],"improve":[41],"system\u2019s":[43],"language":[44,52,60],"modeling":[45],"ability,":[46],"further":[48,71],"attempt":[49],"internal":[51],"model":[53],"as":[54,56],"well":[55],"long":[58],"context":[59],"model.":[61],"Given":[62],"limited":[64],"data":[66,73,86],"in":[67,126],"investigate":[72],"augmentation":[74],"speed":[77],"perturbation,":[78],"pitch":[79],"shifting,":[80],"speech":[81],"codec,":[82],"SpecAugment":[83],"synthetic":[85],"from":[87,103],"text-to-speech":[88],"(TTS).":[89],"Finally,":[90],"ROVER-based":[93],"score":[94],"fusion":[95],"make":[97],"full":[98],"use":[99],"complementary":[101],"hypotheses":[102],"different":[104],"models.":[105],"Our":[106],"achieves":[109],"16.87%":[110],"on":[111,116],"mix":[112],"error":[113],"rate":[114],"(MER)":[115],"test":[118],"set":[119],"comes":[121],"2nd":[124],"place":[125],"challenge":[128],"ranking.":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
