{"id":"https://openalex.org/W4405709772","doi":"https://doi.org/10.1109/iscslp63861.2024.10800631","title":"Non-Intrusive Audio Quality Assessment Based on Deep Neural Network for Subjective MOS Prediction","display_name":"Non-Intrusive Audio Quality Assessment Based on Deep Neural Network for Subjective MOS Prediction","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709772","doi":"https://doi.org/10.1109/iscslp63861.2024.10800631"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5102576002","display_name":"Xinwen Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinwen Yue","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology,Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011294101","display_name":"Yupei Zhang","orcid":"https://orcid.org/0009-0007-0752-0630"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yupei Zhang","raw_affiliation_strings":["NIO,Audio and Acoustics Technology Department,Shanghai"],"affiliations":[{"raw_affiliation_string":"NIO,Audio and Acoustics Technology Department,Shanghai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040549851","display_name":"Jianqian Zhang","orcid":"https://orcid.org/0009-0000-3949-2549"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqian Zhang","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology,Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390297","display_name":"Zhiyu Li","orcid":"https://orcid.org/0009-0008-3196-7739"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Li","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology,Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378497","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-3653-9951"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology,Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077965872","display_name":"Shenghui Zhao","orcid":"https://orcid.org/0000-0002-0844-2319"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenghui Zhao","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology,Beijing","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102576002"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27154942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9348999857902527,"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/T11309","display_name":"Music and Audio Processing","score":0.9348999857902527,"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":0.7349565029144287},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6864281296730042},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5155925154685974},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5136284232139587},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49862098693847656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49172690510749817},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3202522099018097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7349565029144287},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6864281296730042},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5155925154685974},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5136284232139587},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49862098693847656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49172690510749817},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3202522099018097},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1920160043","https://openalex.org/W1989337816","https://openalex.org/W2067295501","https://openalex.org/W2076608692","https://openalex.org/W2108708552","https://openalex.org/W2511311723","https://openalex.org/W2763188033","https://openalex.org/W2922332774","https://openalex.org/W2963403924","https://openalex.org/W2963723765","https://openalex.org/W2972394484","https://openalex.org/W2973231102","https://openalex.org/W3037038648","https://openalex.org/W3083776549","https://openalex.org/W3161558238","https://openalex.org/W3196475561","https://openalex.org/W4225319489","https://openalex.org/W4297841702","https://openalex.org/W6631190155","https://openalex.org/W6639363673","https://openalex.org/W6732646663","https://openalex.org/W6809688645"],"related_works":["https://openalex.org/W2391251536","https://openalex.org/W2961085424","https://openalex.org/W2362198218","https://openalex.org/W2019521278","https://openalex.org/W1984922432","https://openalex.org/W2375008505","https://openalex.org/W1982750869","https://openalex.org/W2085756966","https://openalex.org/W2350679292","https://openalex.org/W2086348228"],"abstract_inverted_index":{"Non-intrusive":[0],"audio":[1,16,34,57,72],"quality":[2,31,35,58],"assessment,":[3,32],"particularly":[4],"for":[5,9,28,66,79,92],"subjective":[6,67,86],"MOS":[7,68],"prediction":[8,69],"music":[10],"signal,":[11],"is":[12],"crucial":[13],"in":[14,133],"real-time":[15],"communication":[17],"and":[18,45,82,85,106],"playback":[19],"systems.":[20],"While":[21],"network-based":[22],"methods":[23,132],"have":[24],"been":[25],"extensively":[26],"used":[27],"objective":[29,84],"speech":[30],"evaluating":[33],"presents":[36],"a":[37,55,107],"greater":[38],"challenge":[39],"due":[40],"to":[41,112],"higher":[42],"sampling":[43],"rates":[44],"more":[46],"complex":[47],"signal":[48,80],"spectrum.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,99],"design":[54],"non-intrusive":[56],"assessment":[59,131],"system":[60,126],"based":[61],"on":[62,95],"deep":[63],"neural":[64],"network":[65],"of":[70,109,116],"distorted":[71],"signals.":[73],"Mixed":[74],"perceptual":[75],"features":[76],"are":[77,88],"extracted":[78],"analysis,":[81],"both":[83],"indicators":[87],"utilized":[89],"as":[90],"labels":[91],"two-step":[93],"training":[94],"simulated":[96],"data.":[97],"Besides,":[98],"apply":[100],"improved":[101],"convolution":[102],"layers,":[103,105],"attention":[104],"type":[108],"new":[110],"loss":[111],"improve":[113],"the":[114,124],"performance":[115],"our":[117],"model.":[118],"The":[119],"experimental":[120],"results":[121],"show":[122],"that":[123],"proposed":[125],"performs":[127],"better":[128],"than":[129],"conventional":[130],"correlation.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}