{"id":"https://openalex.org/W4375868974","doi":"https://doi.org/10.1109/icassp49357.2023.10097011","title":"The NPU-ASLP System for Audio-Visual Speech Recognition in MISP 2022 Challenge","display_name":"The NPU-ASLP System for Audio-Visual Speech Recognition in MISP 2022 Challenge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868974","doi":"https://doi.org/10.1109/icassp49357.2023.10097011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"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":true,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101808140","display_name":"Wang He","orcid":"https://orcid.org/0000-0002-3436-1299"},"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":"He Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072425459","display_name":"Bingshen Mu","orcid":"https://orcid.org/0009-0009-7797-865X"},"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":"Bingshen Mu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437589","display_name":"Ao Zhang","orcid":"https://orcid.org/0000-0002-1536-2413"},"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":"Ao Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025104497","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,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101783173"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.8299,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85860925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.7915685176849365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7111945152282715},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6121538877487183},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5612143278121948},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5530110001564026},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.525899350643158},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5089466571807861},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4856356680393219},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.466754674911499},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4460182189941406},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44050827622413635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43370482325553894},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.39651742577552795},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3348362147808075},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.10142216086387634},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09347209334373474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915685176849365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7111945152282715},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6121538877487183},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5612143278121948},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5530110001564026},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.525899350643158},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5089466571807861},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4856356680393219},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.466754674911499},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4460182189941406},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44050827622413635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43370482325553894},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.39651742577552795},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3348362147808075},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.10142216086387634},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09347209334373474},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1983812858","https://openalex.org/W2900212944","https://openalex.org/W2962780374","https://openalex.org/W4224933780","https://openalex.org/W4284973286","https://openalex.org/W4297841387","https://openalex.org/W4319862255","https://openalex.org/W4324312102","https://openalex.org/W4372317224","https://openalex.org/W6839026989"],"related_works":["https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2144208207","https://openalex.org/W1577485118","https://openalex.org/W1937501964","https://openalex.org/W78370326","https://openalex.org/W3178100380","https://openalex.org/W3161590371","https://openalex.org/W3119492978","https://openalex.org/W2113810833"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,90],"NPU-ASLP":[4],"system":[5,91],"for":[6,45],"the":[7,15,25,53,67,81,105,116],"Audio-Visual":[8],"Diarization":[9],"and":[10,30,41,57,102,107,110],"Recognition":[11],"(AVDR)":[12],"task":[13],"in":[14,115],"Multi-modal":[16],"Information":[17],"based":[18,59,72],"Speech":[19],"Processing":[20],"(MISP)":[21],"2022":[22],"Challenge.":[23],"Specifically,":[24],"weighted":[26],"prediction":[27],"error":[28,97],"(WPE)":[29],"guided":[31],"source":[32],"separation":[33],"(GSS)":[34],"techniques":[35],"are":[36],"used":[37],"to":[38],"reduce":[39],"reverberation":[40],"generate":[42],"clean":[43],"signals":[44],"each":[46],"single":[47],"speaker":[48],"first.":[49],"Then,":[50],"we":[51],"explore":[52],"effectiveness":[54],"of":[55,66,100],"Branchformer":[56],"E-Branchformer":[58],"ASR":[60],"systems.":[61],"To":[62],"better":[63],"make":[64],"use":[65],"visual":[68],"modality,":[69],"a":[70,93,112],"cross-attention":[71],"multi-modal":[73],"fusion":[74],"module":[75],"is":[76],"proposed,":[77],"which":[78],"explicitly":[79],"learns":[80],"contextual":[82],"relationship":[83],"between":[84],"different":[85],"modalities.":[86],"Experiments":[87],"show":[88],"that":[89],"achieves":[92],"concatenated":[94],"minimum-permutation":[95],"character":[96],"rate":[98],"(cpCER)":[99],"28.13%":[101],"31.21%":[103],"on":[104],"Dev":[106],"Eval":[108],"set,":[109],"obtains":[111],"second":[113],"place":[114],"challenge.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}