{"id":"https://openalex.org/W3015706940","doi":"https://doi.org/10.1109/icassp40776.2020.9053951","title":"Full-Reference Speech Quality Estimation with Attentional Siamese Neural Networks","display_name":"Full-Reference Speech Quality Estimation with Attentional Siamese Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015706940","doi":"https://doi.org/10.1109/icassp40776.2020.9053951","mag":"3015706940"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.00783","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069979525","display_name":"Gabriel Mittag","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gabriel Mittag","raw_affiliation_strings":["Quality and Usability Lab, Technische Universit\u00e4t Berlin, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quality and Usability Lab, Technische Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075001284","display_name":"Sebastian M\u00f6ller","orcid":"https://orcid.org/0000-0003-3057-0760"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Moller","raw_affiliation_strings":["Quality and Usability Lab, Technische Universit\u00e4t Berlin, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quality and Usability Lab, Technische Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":1.8075,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86702849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"346","last_page":"350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9975000023841858,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7616277933120728},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.6460852026939392},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6384842395782471},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6119247078895569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4894348680973053},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41909945011138916},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07129120826721191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616277933120728},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6460852026939392},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6384842395782471},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6119247078895569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4894348680973053},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41909945011138916},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07129120826721191},{"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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.00783","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.00783","pdf_url":"https://arxiv.org/pdf/2105.00783","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.00783","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.00783","pdf_url":"https://arxiv.org/pdf/2105.00783","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1728888090","https://openalex.org/W2103934944","https://openalex.org/W2561217444","https://openalex.org/W2563786098","https://openalex.org/W2889128201","https://openalex.org/W2904306984","https://openalex.org/W2922332774","https://openalex.org/W2937033898","https://openalex.org/W2938881288","https://openalex.org/W2939156090","https://openalex.org/W2944426940","https://openalex.org/W2944536795","https://openalex.org/W2963403924","https://openalex.org/W2972419867","https://openalex.org/W2973403216","https://openalex.org/W3100498948","https://openalex.org/W4289106758","https://openalex.org/W6756780969","https://openalex.org/W6760220131","https://openalex.org/W6762105933","https://openalex.org/W6767534469"],"related_works":["https://openalex.org/W2576994247","https://openalex.org/W2608353378","https://openalex.org/W4249206767","https://openalex.org/W2563559453","https://openalex.org/W2382330008","https://openalex.org/W1519970947","https://openalex.org/W4243860260","https://openalex.org/W4383503847","https://openalex.org/W2391251536","https://openalex.org/W2342695897"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,12,19,30,73],"full-reference":[6],"speech":[7,66,83,100],"quality":[8,101],"prediction":[9],"model":[10,17],"with":[11,54],"deep":[13],"learning":[14],"approach.":[15],"The":[16,44,68],"determines":[18],"feature":[20],"representation":[21],"of":[22],"the":[23,26,37,52,64,77,92],"reference":[24,94],"and":[25,58,89],"degraded":[27],"signal":[28,95],"through":[29,86],"Siamese":[31],"recurrent":[32],"convolutional":[33],"network":[34,70],"that":[35,80,103],"shares":[36],"weights":[38],"for":[39,76,82],"both":[40],"signals":[41,53,84],"as":[42],"input.":[43],"resulting":[45],"features":[46],"are":[47,59,104],"then":[48],"used":[49],"to":[50,62],"align":[51],"an":[55],"attention":[56],"mechanism":[57],"finally":[60],"combined":[61],"estimate":[63],"overall":[65],"quality.":[67],"proposed":[69],"architecture":[71],"represents":[72],"simple":[74],"solution":[75],"time-alignment":[78],"problem":[79],"occurs":[81],"transmitted":[85],"Voice-Over-IP":[87],"networks":[88],"shows":[90],"how":[91],"clean":[93],"can":[96],"be":[97],"incorporated":[98],"into":[99],"models":[102],"based":[105],"on":[106],"end-to-end":[107],"trained":[108],"neural":[109],"networks.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2020-04-17T00:00:00"}
