{"id":"https://openalex.org/W4405709476","doi":"https://doi.org/10.1109/iscslp63861.2024.10800189","title":"SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features","display_name":"SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709476","doi":"https://doi.org/10.1109/iscslp63861.2024.10800189"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800189","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/A5089019283","display_name":"Yufei Shi","orcid":"https://orcid.org/0000-0002-6999-0191"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu-Fei Shi","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072371384","display_name":"Ye-Xin Lu","orcid":"https://orcid.org/0009-0009-8026-0702"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye-Xin Lu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067982618","display_name":"Hui-Peng Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui-Peng Du","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5089019283"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3316,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6902759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9905999898910522,"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":0.9905999898910522,"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/T11309","display_name":"Music and Audio Processing","score":0.9812999963760376,"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":0.7590562701225281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4592573046684265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45315834879875183},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44103366136550903},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4125230014324188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590562701225281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4592573046684265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45315834879875183},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44103366136550903},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4125230014324188}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800189","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":[{"display_name":"Reduced inequalities","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1728888090","https://openalex.org/W2067295501","https://openalex.org/W2107860279","https://openalex.org/W2962780374","https://openalex.org/W2963403924","https://openalex.org/W2964058413","https://openalex.org/W2972394484","https://openalex.org/W3097777922","https://openalex.org/W3161558238","https://openalex.org/W3196225973","https://openalex.org/W3196475561","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W3209059054","https://openalex.org/W4223503417","https://openalex.org/W4224939568","https://openalex.org/W4225956675","https://openalex.org/W4296068832","https://openalex.org/W4296068974","https://openalex.org/W4296070386","https://openalex.org/W4311167834","https://openalex.org/W4372260498","https://openalex.org/W4372263384","https://openalex.org/W4385823334","https://openalex.org/W4386076493","https://openalex.org/W4391021782","https://openalex.org/W4395959004","https://openalex.org/W4402112619","https://openalex.org/W6633117090","https://openalex.org/W6729924827","https://openalex.org/W6772349387","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Assessing":[0],"the":[1,16,28,96,109,129,142,150,160,168,173],"naturalness":[2],"of":[3,19,34,61,90,112,123,175],"speech":[4,20,35,52,62,91],"using":[5],"mean":[6],"opinion":[7],"score":[8],"(MOS)":[9],"prediction":[10,25,70,81,130,157],"models":[11,26,46,158],"has":[12],"positive":[13],"implications":[14],"for":[15,53,64],"auto-matic":[17],"evaluation":[18,177],"synthesis":[21],"systems.":[22],"Early":[23],"MOS":[24,54,65,80,144,156],"took":[27],"raw":[29],"waveform":[30],"or":[31],"amplitude":[32],"spectrum":[33],"as":[36],"input,":[37],"whereas":[38],"more":[39],"advanced":[40],"methods":[41,57],"employed":[42],"self-supervised-learning":[43],"(SSL)":[44],"based":[45],"to":[47,92,103,116,140,172],"extract":[48,104,117],"semantic":[49,105],"representations":[50,106],"from":[51],"prediction.":[55],"These":[56,120],"utilized":[58],"limited":[59],"aspects":[60],"information":[63,89],"prediction,":[66],"resulting":[67],"in":[68,73],"restricted":[69],"accuracy.":[71],"Therefore,":[72],"this":[74],"paper,":[75],"we":[76],"propose":[77],"SAMOS,":[78],"a":[79,100,113],"model":[82],"that":[83,149],"leverages":[84,99],"both":[85],"Semantic":[86],"and":[87,107,136,163],"Acoustic":[88],"be":[93],"assessed.":[94],"Specifically,":[95],"proposed":[97,151],"SAMOS":[98,152],"pretrained":[101,114],"wav2vec2":[102],"uses":[108],"feature":[110],"extractor":[111],"BiVocoder":[115],"acoustic":[118],"features.":[119],"two":[121],"types":[122],"features":[124],"are":[125],"then":[126],"fed":[127],"into":[128],"network,":[131],"which":[132],"includes":[133],"multitask":[134],"heads":[135],"an":[137],"aggregation":[138],"layer,":[139],"obtain":[141],"final":[143],"score.":[145],"Ex-perimental":[146],"results":[147,174],"demonstrate":[148],"outperforms":[153],"current":[154],"state-of-the-art":[155],"on":[159,167],"BVCC":[161],"dataset":[162],"performs":[164],"comparable":[165],"performance":[166],"BC2019":[169],"dataset,":[170],"according":[171],"system-level":[176],"metrics.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}