{"id":"https://openalex.org/W3197822518","doi":"https://doi.org/10.21437/interspeech.2021-46","title":"Temporal Convolutional Network with Frequency Dimension Adaptive Attention for Speech Enhancement","display_name":"Temporal Convolutional Network with Frequency Dimension Adaptive Attention for Speech Enhancement","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197822518","doi":"https://doi.org/10.21437/interspeech.2021-46","mag":"3197822518"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-46","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://hdl.handle.net/10072/411829","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042675934","display_name":"Qiquan Zhang","orcid":"https://orcid.org/0000-0001-5089-6317"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiquan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748969","display_name":"Qi Song","orcid":"https://orcid.org/0000-0002-1726-7858"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041494929","display_name":"Aaron Nicolson","orcid":"https://orcid.org/0000-0002-7163-1809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aaron Nicolson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523731","display_name":"Tian Lan","orcid":"https://orcid.org/0000-0001-6381-7657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"166","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9955999851226807,"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/T13289","display_name":"Infant Health and Development","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.7336120009422302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6780874133110046},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5711313486099243},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46807560324668884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33554816246032715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1241874098777771}],"concepts":[{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.7336120009422302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6780874133110046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5711313486099243},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46807560324668884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33554816246032715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1241874098777771},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-46","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/411829","is_oa":true,"landing_page_url":"http://hdl.handle.net/10072/411829","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"}],"best_oa_location":{"id":"pmh:oai:research-repository.griffith.edu.au:10072/411829","is_oa":true,"landing_page_url":"http://hdl.handle.net/10072/411829","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W2121973264","https://openalex.org/W2153894152","https://openalex.org/W2561557072","https://openalex.org/W2678916739","https://openalex.org/W2792764867","https://openalex.org/W2884585870","https://openalex.org/W2889133076","https://openalex.org/W2914067823","https://openalex.org/W2952979007","https://openalex.org/W2963420686","https://openalex.org/W3008487564","https://openalex.org/W3017350693","https://openalex.org/W3047107405"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W2782782444"],"abstract_inverted_index":{"Despite":[0],"much":[1],"progress,":[2],"most":[3],"temporal":[4,19],"convolutional":[5],"networks":[6],"(TCN)":[7],"based":[8],"speech":[9,23,33,64,94],"enhancement":[10],"models":[11],"are":[12],"mainly":[13],"focused":[14],"on":[15],"modeling":[16],"the":[17,29,55,59,69,80],"long-term":[18],"contextual":[20],"dependencies":[21],"of":[22,32,72,93],"frames,":[24],"without":[25],"taking":[26],"into":[27],"account":[28],"distribution":[30],"information":[31,65],"signal":[34],"in":[35,91],"frequency":[36,44],"dimension.":[37],"In":[38],"this":[39],"study,":[40],"we":[41],"propose":[42],"a":[43],"dimension":[45],"adaptive":[46],"attention":[47],"(FAA)":[48],"mechanism":[49,83],"to":[50,86,111],"improve":[51],"TCNs,":[52],"which":[53],"guides":[54],"model":[56],"selectively":[57],"emphasize":[58],"frequency-wise":[60],"features":[61],"with":[62],"important":[63],"and":[66,99],"also":[67],"improves":[68],"representation":[70],"capability":[71],"network.":[73],"Our":[74],"extensive":[75],"experimental":[76],"investigation":[77],"demonstrates":[78],"that":[79],"proposed":[81],"FAA":[82],"is":[84],"able":[85],"consistently":[87],"provide":[88],"significant":[89],"improvements":[90],"terms":[92],"quality":[95],"(PESQ),":[96],"intelligibility":[97],"(STOI)":[98],"three":[100],"other":[101],"composite":[102],"metrics.":[103],"More":[104],"promisingly,":[105],"it":[106],"has":[107],"better":[108],"generalization":[109],"ability":[110],"real-world":[112],"noisy":[113],"environment.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}