{"id":"https://openalex.org/W4385823276","doi":"https://doi.org/10.21437/interspeech.2023-801","title":"Audio-Visual Fusion using Multiscale Temporal Convolutional Attention for Time-Domain Speech Separation","display_name":"Audio-Visual Fusion using Multiscale Temporal Convolutional Attention for Time-Domain Speech Separation","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823276","doi":"https://doi.org/10.21437/interspeech.2023-801"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-801","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5032068623","display_name":"Debang Liu","orcid":"https://orcid.org/0000-0002-7411-9683"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Debang Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425391","display_name":"Tianqi Zhang","orcid":"https://orcid.org/0000-0002-7129-5622"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianqi Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026658144","display_name":"Mads Gr\u00e6sb\u00f8ll Christensen","orcid":"https://orcid.org/0000-0003-3586-7969"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mads Gr\u00e6sb\u00f8ll Christensen","raw_affiliation_strings":["Aalborg University, The Technical Faculty of IT and Design, DK"],"affiliations":[{"raw_affiliation_string":"Aalborg University, The Technical Faculty of IT and Design, DK","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101478527","display_name":"Ying Wei","orcid":"https://orcid.org/0000-0001-8217-4765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076399232","display_name":"Zeliang An","orcid":"https://orcid.org/0000-0002-9947-9634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeliang An","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032068623"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09615023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3694","last_page":"3698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9193999767303467,"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/computer-science","display_name":"Computer science","score":0.77684485912323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6420319080352783},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6263141632080078},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5584619641304016},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5348851084709167},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4496147036552429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42423027753829956},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11255025863647461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77684485912323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6420319080352783},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6263141632080078},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5584619641304016},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5348851084709167},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4496147036552429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42423027753829956},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11255025863647461},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":2,"locations":[{"id":"doi:10.21437/interspeech.2023-801","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/2693ba9f-9005-4cee-92ff-ee4d83e2f224","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/2693ba9f-9005-4cee-92ff-ee4d83e2f224","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Liu, D, Zhang, T, Christensen, M G, Wei, Y & An, Z 2023, 'Audio-Visual Fusion using Multiscale Temporal Convolutional Attention for Time-Domain Speech Separation', Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2023-August, pp. 3694-3698. https://doi.org/10.21437/Interspeech.2023-801","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"Audio-only":[0],"speech":[1,64,104],"separation":[2,14,18,65,101,105,129],"methods":[3,19],"cannot":[4],"fully":[5],"exploit":[6],"audio-visual":[7,17,32,60],"correlation":[8],"information":[9],"of":[10,24,52,84,96],"speaker,":[11],"which":[12],"limits":[13],"performance.":[15,130],"Additionally,":[16],"usually":[20],"adopt":[21],"traditional":[22],"idea":[23],"feature":[25],"splicing":[26],"and":[27,92,114,128],"linear":[28],"mapping":[29],"to":[30,38,78,98,116],"fuse":[31],"features,":[33],"this":[34,46],"approach":[35],"requires":[36],"us":[37],"think":[39],"more":[40],"about":[41],"fusion":[42,93],"process.":[43],"Therefore,":[44],"in":[45,123],"paper,":[47],"combining":[48],"with":[49],"the":[50],"changes":[51],"speaker":[53],"mouth":[54],"landmarks,":[55],"we":[56,70],"propose":[57],"a":[58,72,100],"time-domain":[59],"temporal":[61,74],"convolution":[62],"attention":[63,76],"method":[66],"(AVTA).":[67],"In":[68],"AVTA,":[69],"design":[71],"multiscale":[73],"convolutional":[75],"(MTCA)":[77],"better":[79,121],"focus":[80],"on":[81],"contextual":[82],"dependencies":[83],"time":[85],"sequences.":[86],"We":[87],"then":[88],"use":[89],"sequence":[90],"learning":[91],"network":[94],"composed":[95],"MTCA":[97],"build":[99],"model":[102],"for":[103],"task.":[106],"On":[107],"different":[108],"datasets,":[109],"AVTA":[110,119],"achieves":[111],"competitive":[112],"performance,":[113],"compared":[115],"baseline":[117],"methods,":[118],"is":[120],"balanced":[122],"training":[124],"cost,":[125],"computational":[126],"complexity":[127]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}