{"id":"https://openalex.org/W2889128201","doi":"https://doi.org/10.21437/interspeech.2018-1374","title":"Prediction of Perceived Speech Quality Using Deep Machine Listening","display_name":"Prediction of Perceived Speech Quality Using Deep Machine Listening","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889128201","doi":"https://doi.org/10.21437/interspeech.2018-1374","mag":"2889128201"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1374","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publica.fraunhofer.de/documents/N-581824.html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011528026","display_name":"Jasper Ooster","orcid":"https://orcid.org/0000-0003-1498-3776"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jasper Ooster","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080820413","display_name":"Rainer H\u00fcber","orcid":"https://orcid.org/0000-0001-7241-2037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rainer Huber","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067491941","display_name":"Bernd T. Meyer","orcid":"https://orcid.org/0000-0001-9190-2111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernd T. Meyer","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011528026"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4771,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90393158,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"976","last_page":"980"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9871000051498413,"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":0.7365323901176453},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.7125516533851624},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6691689491271973},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6345158815383911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40564554929733276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33835697174072266},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13124147057533264},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.06344878673553467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365323901176453},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7125516533851624},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6691689491271973},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6345158815383911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40564554929733276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33835697174072266},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13124147057533264},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.06344878673553467},{"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":3,"locations":[{"id":"doi:10.21437/interspeech.2018-1374","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:fraunhofer.de:N-581824","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-581824.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/407529","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/407529","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:fraunhofer.de:N-581824","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-581824.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1989351718","https://openalex.org/W1993882792","https://openalex.org/W2002342963","https://openalex.org/W2043429285","https://openalex.org/W2048741136","https://openalex.org/W2124629003","https://openalex.org/W2131342762","https://openalex.org/W2140651276","https://openalex.org/W2160815625","https://openalex.org/W2533523411","https://openalex.org/W2587464121","https://openalex.org/W2749744051","https://openalex.org/W2778517680","https://openalex.org/W2895866335"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Subjective":[0],"ratings":[1,75],"of":[2,31,45,86,150,191,194],"speech":[3,12,41,79,112],"quality":[4,80,118,198],"(SQ)":[5],"are":[6],"essential":[7],"for":[8,11,24,61],"evaluating":[9],"algorithms":[10],"transmission":[13],"and":[14,104,113,135,165],"enhancement.":[15],"In":[16,138],"this":[17,68],"paper":[18],"we":[19,187],"explore":[20],"a":[21,32,38,122],"non-intrusive":[22],"model":[23,133,145,183],"SQ":[25,65,87],"prediction":[26],"based":[27],"on":[28,197],"the":[29,50,55,77,144,156,160,166,173,181,189,192],"output":[30,134],"deep":[33],"neural":[34],"net":[35,51],"(DNN)":[36],"from":[37,49,76],"regular":[39],"automatic":[40],"recognizer.":[42],"The":[43,64],"degradation":[44,88],"phoneme":[46],"probabilities":[47],"obtained":[48],"is":[52,70,109,119,126,153,178],"quantified":[53],"with":[54,67,72,159],"mean":[56],"temporal":[57],"distance":[58],"proposed":[59],"earlier":[60],"multi-stream":[62],"ASR.":[63],"predicted":[66],"method":[69],"compared":[71],"average":[73,148],"subject":[74],"TCD-VoIP":[78],"database":[81],"that":[82,89],"covers":[83],"several":[84],"effects":[85],"can":[90],"occur":[91],"in":[92],"VoIP":[93],"applications":[94],"such":[95],"as":[96],"clipping,":[97],"packet":[98],"loss,":[99],"echo":[100],"effects,":[101],"background":[102],"noise":[103],"competing":[105,123],"speakers.":[106],"Our":[107],"approach":[108],"tailored":[110],"to":[111,184],"therefore":[114],"not":[115,179],"applicable":[116],"when":[117],"degraded":[120],"by":[121,128],"speaker,":[124],"which":[125,152],"reflected":[127],"an":[129,147],"insignificant":[130],"correlation":[131,149,157],"between":[132],"subjective":[136],"SQ.":[137],"all":[139],"other":[140],"conditions":[141],"mentioned":[142],"above,":[143],"reaches":[146],"r=0.87,":[151],"higher":[154],"than":[155],"achieved":[158],"baseline":[161],"ITU-T":[162],"P.563":[163],"(r=0.71)":[164],"American":[167],"National":[168],"Standard":[169],"ANIQUE+":[170],"(r=0.75).":[171],"Since":[172],"most":[174],"robust":[175],"ASR":[176],"system":[177],"necessarily":[180],"best":[182],"predict":[185],"SQ,":[186],"investigate":[188],"effect":[190],"amount":[193],"training":[195],"data":[196],"prediction.":[199]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}