{"id":"https://openalex.org/W3016129867","doi":"https://doi.org/10.1109/icassp40776.2020.9053591","title":"T-GSA: Transformer with Gaussian-Weighted Self-Attention for Speech Enhancement","display_name":"T-GSA: Transformer with Gaussian-Weighted Self-Attention for Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016129867","doi":"https://doi.org/10.1109/icassp40776.2020.9053591","mag":"3016129867"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053591","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":["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/A5100344655","display_name":"Jaeyoung Kim","orcid":"https://orcid.org/0000-0002-4830-0454"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeyoung Kim","raw_affiliation_strings":["SOC R&D, Samsung Semiconductor, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SOC R&D, Samsung Semiconductor, Inc","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022805456","display_name":"Mostafa El\u2010Khamy","orcid":"https://orcid.org/0000-0001-9421-6037"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mostafa El-Khamy","raw_affiliation_strings":["SOC R&D, Samsung Semiconductor, Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SOC R&D, Samsung Semiconductor, Inc., USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331815","display_name":"Jungwon Lee","orcid":"https://orcid.org/0000-0001-8922-063X"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jungwon Lee","raw_affiliation_strings":["SOC R&D, Samsung Semiconductor, Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SOC R&D, Samsung Semiconductor, Inc., USA","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":189,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6649","last_page":"6653"},"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":0.9995999932289124,"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":0.9995999932289124,"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/transformer","display_name":"Transformer","score":0.7957836389541626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387233972549438},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5799810886383057},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5770173072814941},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5009114742279053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49776437878608704},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4958542287349701},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47414132952690125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.333431601524353},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3207564949989319},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2965836524963379},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09838932752609253},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08847132325172424}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7957836389541626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387233972549438},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5799810886383057},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5770173072814941},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5009114742279053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49776437878608704},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4958542287349701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47414132952690125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.333431601524353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3207564949989319},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2965836524963379},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09838932752609253},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08847132325172424},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053591","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5600000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1506438021","https://openalex.org/W1635512741","https://openalex.org/W1924770834","https://openalex.org/W1983108229","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2094721231","https://openalex.org/W2120847449","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2141411743","https://openalex.org/W2144404214","https://openalex.org/W2357464558","https://openalex.org/W2603567530","https://openalex.org/W2802304149","https://openalex.org/W2912191105","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2964089206","https://openalex.org/W3147539069","https://openalex.org/W4385245566","https://openalex.org/W6640212811","https://openalex.org/W6706288655","https://openalex.org/W6739901393","https://openalex.org/W6751445809","https://openalex.org/W6758407994"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2903810591","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2890256614","https://openalex.org/W3098873988","https://openalex.org/W2949454572","https://openalex.org/W3066373881","https://openalex.org/W2970247882"],"abstract_inverted_index":{"Transformer":[0,83,118],"neural":[1,16],"networks":[2,17],"(TNN)":[3],"demonstrated":[4],"state-ofart":[5],"performance":[6],"on":[7],"many":[8],"natural":[9],"language":[10],"processing":[11],"(NLP)":[12],"tasks,":[13,40],"replacing":[14],"recurrent":[15],"(RNNs),":[18],"such":[19],"as":[20],"LSTMs":[21],"or":[22],"GRUs.":[23],"However,":[24],"TNNs":[25],"did":[26],"not":[27,54],"perform":[28],"well":[29],"in":[30],"speech":[31],"enhancement,":[32],"whose":[33,88],"contextual":[34],"nature":[35],"is":[36,45,71],"different":[37],"than":[38],"NLP":[39],"like":[41],"machine":[42],"translation.":[43],"Self-attention":[44],"a":[46,82],"core":[47],"building":[48],"block":[49],"of":[50,58],"the":[51,64,95,107,117],"Transformer,":[52],"which":[53],"only":[55],"enables":[56],"parallelization":[57],"sequence":[59],"computation,":[60],"but":[61],"also":[62],"provides":[63],"constant":[65],"path":[66],"length":[67],"between":[68,97],"symbols":[69],"that":[70,106],"essential":[72],"to":[73,94,116],"learning":[74],"long-range":[75],"dependencies.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"propose":[81],"with":[84],"Gaussian-weighted":[85],"self-attention":[86],"(T-GSA),":[87],"attention":[89],"weights":[90],"are":[91],"attenuated":[92],"according":[93],"distance":[96],"target":[98],"and":[99,119],"context":[100],"symbols.":[101],"The":[102],"experimental":[103],"results":[104],"show":[105],"proposed":[108],"T-GSA":[109],"has":[110],"significantly":[111],"improved":[112],"speech-enhancement":[113],"performance,":[114],"compared":[115],"RNNs.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":36},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}