{"id":"https://openalex.org/W3164201234","doi":"https://doi.org/10.1186/s13636-021-00209-4","title":"Neural network-based non-intrusive speech quality assessment using attention pooling function","display_name":"Neural network-based non-intrusive speech quality assessment using attention pooling function","publication_year":2021,"publication_date":"2021-05-17","ids":{"openalex":"https://openalex.org/W3164201234","doi":"https://doi.org/10.1186/s13636-021-00209-4","mag":"3164201234"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-021-00209-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00209-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00209-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00209-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100348904","display_name":"Miao Liu","orcid":"https://orcid.org/0000-0002-6650-9972"},"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":"Miao Liu","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","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, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075613420","display_name":"Weiming Yi","orcid":"https://orcid.org/0009-0005-5217-5966"},"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"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Yi","raw_affiliation_strings":["Key Laboratory of Language, Cognition and Computation Ministry of Industry and Information Technology, School of Foreign Languages, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Language, Cognition and Computation Ministry of Industry and Information Technology, School of Foreign Languages, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I890469752","https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100453075","display_name":"Fang Liu","orcid":"https://orcid.org/0000-0002-5669-9354"},"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"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Liu","raw_affiliation_strings":["Key Laboratory of Language, Cognition and Computation Ministry of Industry and Information Technology, School of Foreign Languages, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Language, Cognition and Computation Ministry of Industry and Information Technology, School of Foreign Languages, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I890469752","https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100348904"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.926,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73761615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2021","issue":"1","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":0.9998999834060669,"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":0.9998999834060669,"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":0.9976000189781189,"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":0.9915000200271606,"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/pooling","display_name":"Pooling","score":0.9133350253105164},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.765654981136322},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.6410394906997681},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6036760807037354},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.590728223323822},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.5682948231697083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5522637963294983},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5288922190666199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5073835253715515},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4868304133415222},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46436354517936707},{"id":"https://openalex.org/keywords/quality-score","display_name":"Quality Score","score":0.4432534873485565},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36939483880996704},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12562140822410583},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1214083731174469},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.060181766748428345}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9133350253105164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765654981136322},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.6410394906997681},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6036760807037354},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.590728223323822},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.5682948231697083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5522637963294983},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5288922190666199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5073835253715515},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4868304133415222},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46436354517936707},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.4432534873485565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36939483880996704},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12562140822410583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1214083731174469},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.060181766748428345},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-021-00209-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00209-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00209-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b7472589c34841948a810babad98fb41","is_oa":true,"landing_page_url":"https://doaj.org/article/b7472589c34841948a810babad98fb41","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2021, Iss 1, Pp 1-10 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-021-00209-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00209-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00209-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1938823714","display_name":null,"funder_award_id":"61620106002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4952363744","display_name":null,"funder_award_id":"No.62071039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6471985988","display_name":null,"funder_award_id":"62071039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3164201234.pdf","grobid_xml":"https://content.openalex.org/works/W3164201234.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1600744878","https://openalex.org/W1665214252","https://openalex.org/W1964357740","https://openalex.org/W2064675550","https://openalex.org/W2142690424","https://openalex.org/W2144404214","https://openalex.org/W2146471910","https://openalex.org/W2163605009","https://openalex.org/W2593239632","https://openalex.org/W2717720943","https://openalex.org/W2766106532","https://openalex.org/W2798579254","https://openalex.org/W2918022439","https://openalex.org/W2922332774","https://openalex.org/W2929602570","https://openalex.org/W2936774411","https://openalex.org/W2944536795","https://openalex.org/W2949117887","https://openalex.org/W2963022469","https://openalex.org/W2963403924","https://openalex.org/W2963610932","https://openalex.org/W2963723765","https://openalex.org/W2964121744","https://openalex.org/W2972394484","https://openalex.org/W3015597694","https://openalex.org/W3015706940","https://openalex.org/W3094550259","https://openalex.org/W3097206152","https://openalex.org/W6603590957","https://openalex.org/W6679338098"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2378767206","https://openalex.org/W1585338487","https://openalex.org/W1997117005","https://openalex.org/W1562127107","https://openalex.org/W1989143878","https://openalex.org/W2794418911","https://openalex.org/W2289086982"],"abstract_inverted_index":{"Abstract":[0],"Recently,":[1],"the":[2,19,24,43,68,93,98,101,123,145],"non-intrusive":[3,46],"speech":[4,34,47,112],"quality":[5,35,48,117],"assessment":[6,36,56],"method":[7,57],"has":[8],"attracted":[9],"a":[10,53,107],"lot":[11],"of":[12,45,84,140,147],"attention":[13,59,94,128],"since":[14],"it":[15],"does":[16],"not":[17],"require":[18],"original":[20],"reference":[21],"signals.":[22],"At":[23],"same":[25],"time,":[26],"neural":[27,54,70],"networks":[28,71],"began":[29],"to":[30,33],"be":[31],"applied":[32],"and":[37,78,89,136,142,151],"achieved":[38],"good":[39],"performance.":[40],"To":[41],"improve":[42],"performance":[44,146],"assessment,":[49],"this":[50],"paper":[51],"proposes":[52],"network-based":[55],"using":[58,127],"pooling":[60,85,95,129],"function.":[61],"The":[62,119],"proposed":[63,124],"systems":[64],"are":[65,104],"based":[66],"on":[67],"convolutional":[69],"(CNNs),":[72],"bidirectional":[73],"long":[74],"short-term":[75],"memory":[76],"(BLSTM),":[77],"CNN-LSTM":[79,125],"structure.":[80],"Comparing":[81],"four":[82],"types":[83],"functions":[86],"both":[87],"theoretically":[88],"experimentally,":[90],"we":[91],"find":[92],"function":[96,130],"performs":[97],"best":[99],"among":[100],"four.":[102],"Experiments":[103],"conducted":[105],"in":[106],"dataset":[108],"containing":[109],"various":[110],"degraded":[111],"signals":[113],"with":[114],"corresponding":[115],"subjective":[116],"scores.":[118],"results":[120],"show":[121],"that":[122],"model":[126],"achieves":[131],"state-of-the-art":[132],"correlation":[133],"coefficient":[134],"(R)":[135],"root-mean-square":[137],"error":[138],"(RMSE)":[139],"0.967":[141],"0.269,":[143],"outperforming":[144],"standardization":[148],"ITU-T":[149],"P.563":[150],"autoencoder-support":[152],"vector":[153],"regression":[154],"method.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}