{"id":"https://openalex.org/W4403294774","doi":"https://doi.org/10.1109/lsp.2024.3478211","title":"EMDSQA: A Neural Speech Quality Assessment Model With Speaker Embedding","display_name":"EMDSQA: A Neural Speech Quality Assessment Model With Speaker Embedding","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403294774","doi":"https://doi.org/10.1109/lsp.2024.3478211"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3478211","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3478211","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lsp.2024.3478211","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007703197","display_name":"Yiya Hao","orcid":"https://orcid.org/0000-0003-1234-4209"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiya Hao","raw_affiliation_strings":["Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Sciences, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1234-4209","affiliations":[{"raw_affiliation_string":"Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Sciences, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011297325","display_name":"Feifei Xiong","orcid":"https://orcid.org/0000-0001-9783-2169"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifei Xiong","raw_affiliation_strings":["Hummingbird Audio Laboratory, Alibaba Group, Hangzhou, China","Hummingbird Audio Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hummingbird Audio Laboratory, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Hummingbird Audio Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107028150","display_name":"Bei Li","orcid":"https://orcid.org/0000-0001-7617-9041"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Li","raw_affiliation_strings":["Hummingbird Audio Laboratory, Alibaba Group, Hangzhou, China","Hummingbird Audio Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hummingbird Audio Laboratory, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Hummingbird Audio Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008847016","display_name":"Nai Ding","orcid":"https://orcid.org/0000-0003-3428-2723"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nai Ding","raw_affiliation_strings":["Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Sciences, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Sciences, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jinwei Feng","orcid":"https://orcid.org/0009-0006-9061-7339"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwei Feng","raw_affiliation_strings":["Hummingbird Audio Laboratory, Alibaba Group, Hangzhou, China","Hummingbird Audio Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-9061-7339","affiliations":[{"raw_affiliation_string":"Hummingbird Audio Laboratory, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Hummingbird Audio Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14609926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"3064","last_page":"3068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937000274658203,"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":0.9937000274658203,"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":0.9790999889373779,"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":0.9129999876022339,"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":0.7509276866912842},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7327356934547424},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5713095664978027},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5494751334190369},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5425089597702026},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4518990218639374},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4369310140609741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.370431125164032},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36003321409225464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509276866912842},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7327356934547424},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5713095664978027},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5494751334190369},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5425089597702026},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4518990218639374},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4369310140609741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.370431125164032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36003321409225464},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3478211","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3478211","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lsp.2024.3478211","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3478211","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1927860575","display_name":null,"funder_award_id":"32222035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W111477576","https://openalex.org/W2955857189","https://openalex.org/W2973062255","https://openalex.org/W3024869864","https://openalex.org/W3025844872","https://openalex.org/W3143367551","https://openalex.org/W3161558238","https://openalex.org/W3176511914","https://openalex.org/W3196475561","https://openalex.org/W3197227964","https://openalex.org/W3206706278","https://openalex.org/W4221144124","https://openalex.org/W4224925682","https://openalex.org/W4225302959","https://openalex.org/W4225319489","https://openalex.org/W4225905067","https://openalex.org/W4319862644","https://openalex.org/W4391020683","https://openalex.org/W4392904540","https://openalex.org/W4392909950","https://openalex.org/W6630809802","https://openalex.org/W6780218876","https://openalex.org/W6784299611","https://openalex.org/W6801588699"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466","https://openalex.org/W2640905660"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,55,93,97,134],"neural":[3],"speech":[4,24,30,53],"quality":[5,25,31,39,64],"assessment":[6,32],"model":[7],"with":[8,139],"speaker":[9,83],"embedding.":[10],"This":[11],"model,":[12],"i.e.,":[13],"EMDSQA,":[14],"can":[15,61],"precisely":[16],"predict":[17],"the":[18,63,72,82,107,140],"Mean":[19],"Opinion":[20],"Score":[21],"(MOS)":[22],"of":[23,51,65],"during":[26],"online":[27,46,66],"communications.":[28],"Intrusive":[29],"methods":[33,60],"such":[34],"as":[35,92],"perceptual":[36],"objective":[37],"listening":[38],"analysis":[40],"(POLQA)":[41],"are":[42],"not":[43,70,105],"practical":[44,113],"for":[45,77,114],"communications":[47],"because":[48],"every":[49],"piece":[50],"degraded":[52],"requires":[54],"corresponding":[56,108],"clean":[57,109],"reference.":[58],"Non-intrusive":[59],"assess":[62],"speech,":[67],"but":[68],"have":[69],"reached":[71],"accuracy":[73],"and":[74,89],"robustness":[75],"required":[76],"real-world":[78,115,123],"applications.":[79,117],"EMDSQA":[80,103,132],"extracts":[81],"embedding":[84],"using":[85],"an":[86],"independent":[87],"pipeline":[88],"feeds":[90],"it":[91,111],"prior":[94],"feature":[95],"to":[96],"self-attention-based":[98],"MOS":[99,141],"prediction":[100],"model.":[101],"Since":[102],"does":[104],"need":[106],"reference,":[110],"is":[112],"communication":[116],"An":[118],"open-source":[119],"test":[120],"corpus,":[121],"featuring":[122],"data,":[124],"was":[125],"also":[126],"developed.":[127],"Experimental":[128],"results":[129],"show":[130],"that":[131],"achieves":[133],"0.92":[135],"Pearson":[136],"correlation":[137],"coefficient":[138],"measured":[142],"from":[143],"humans,":[144],"surpassing":[145],"other":[146],"state-of-the-art":[147],"intrusive":[148],"or":[149],"non-intrusive":[150],"methods.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
