{"id":"https://openalex.org/W4414408728","doi":"https://doi.org/10.1007/s11760-025-04788-z","title":"Audio visual chinese speech recognition in daily scene based on cross modal context encoder","display_name":"Audio visual chinese speech recognition in daily scene based on cross modal context encoder","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414408728","doi":"https://doi.org/10.1007/s11760-025-04788-z"},"language":"en","primary_location":{"id":"doi:10.1007/s11760-025-04788-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11760-025-04788-z","pdf_url":null,"source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-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/A5100365634","display_name":"Yijun Liu","orcid":"https://orcid.org/0000-0003-2395-3747"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]},{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijun Liu","raw_affiliation_strings":["Chongqing Research Institute of Intelligent Mathematics and Autonomous AI, Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China","School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing Research Institute of Intelligent Mathematics and Autonomous AI, Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China","institution_ids":["https://openalex.org/I158842170","https://openalex.org/I168337820"]},{"raw_affiliation_string":"School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004116271","display_name":"Zhihua Qu","orcid":"https://orcid.org/0000-0001-6710-7134"},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Qu","raw_affiliation_strings":["School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692653","display_name":"Jie Li","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]},{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Li","raw_affiliation_strings":["Chongqing Research Institute of Intelligent Mathematics and Autonomous AI, Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China","School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China","School of Ocean and Civil Engineering, Shanghai Jiao Tong University, No. 800, Dongchuan Road, Minhang District, 201109, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing Research Institute of Intelligent Mathematics and Autonomous AI, Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China","institution_ids":["https://openalex.org/I158842170","https://openalex.org/I168337820"]},{"raw_affiliation_string":"School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China","institution_ids":["https://openalex.org/I168337820"]},{"raw_affiliation_string":"School of Ocean and Civil Engineering, Shanghai Jiao Tong University, No. 800, Dongchuan Road, Minhang District, 201109, Shanghai, China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I44675526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100963274","display_name":"Qian Zhang","orcid":"https://orcid.org/0009-0001-8722-6568"},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Zhang","raw_affiliation_strings":["School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427691","display_name":"Bowen Liu","orcid":"https://orcid.org/0000-0002-0644-4687"},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Liu","raw_affiliation_strings":["School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, No. 20, University City East Road, Shapingba District, 401331, Chongqing, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102797076","display_name":"Wujun Chen","orcid":"https://orcid.org/0000-0001-8084-9538"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wujun Chen","raw_affiliation_strings":["School of Ocean and Civil Engineering, Shanghai Jiao Tong University, No. 800, Dongchuan Road, Minhang District, 201109, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Ocean and Civil Engineering, Shanghai Jiao Tong University, No. 800, Dongchuan Road, Minhang District, 201109, Shanghai, China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I44675526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100692653"],"corresponding_institution_ids":["https://openalex.org/I158842170","https://openalex.org/I168337820","https://openalex.org/I183067930","https://openalex.org/I44675526"],"apc_list":{"value":3390,"currency":"USD","value_usd":3390},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24099287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"14","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":0.9986000061035156,"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":0.9986000061035156,"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/T13579","display_name":"Image and Video Stabilization","score":0.9891999959945679,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9851999878883362,"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/connectionism","display_name":"Connectionism","score":0.5810999870300293},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5303999781608582},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44620001316070557},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43709999322891235},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.39500001072883606},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.38040000200271606},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.36980000138282776},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3499999940395355},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.34139999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8422999978065491},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6784999966621399},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5810999870300293},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206999778747559},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.34040001034736633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3264999985694885},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11760-025-04788-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11760-025-04788-z","pdf_url":null,"source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2964283370","https://openalex.org/W2999528291","https://openalex.org/W3097777922","https://openalex.org/W3207628370","https://openalex.org/W4200635083","https://openalex.org/W4221153521","https://openalex.org/W4224933780","https://openalex.org/W4321231565","https://openalex.org/W4372267461","https://openalex.org/W4372267507","https://openalex.org/W4372346152","https://openalex.org/W4372348478","https://openalex.org/W4383532878","https://openalex.org/W4385211299","https://openalex.org/W4392487628","https://openalex.org/W4392780157","https://openalex.org/W4392904484","https://openalex.org/W4394611093","https://openalex.org/W4402111743","https://openalex.org/W4402629542","https://openalex.org/W4406131770","https://openalex.org/W4408295287","https://openalex.org/W4410083766"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
