{"id":"https://openalex.org/W4372265870","doi":"https://doi.org/10.1109/icassp49357.2023.10096693","title":"Ripple Sparse Self-Attention for Monaural Speech Enhancement","display_name":"Ripple Sparse Self-Attention for Monaural Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372265870","doi":"https://doi.org/10.1109/icassp49357.2023.10096693"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5042675934","display_name":"Qiquan Zhang","orcid":"https://orcid.org/0000-0001-5089-6317"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU","SG"],"is_corresponding":false,"raw_author_name":"Qiquan Zhang","raw_affiliation_strings":["University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","Department of Electrical and Computer Engineering, National University of Singapore, Singapore","School of Electrical Engineering and Telecommunications, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Electrical Engineering and Telecommunications, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057187503","display_name":"Hongxu Zhu","orcid":"https://orcid.org/0000-0001-6257-7065"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hongxu Zhu","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085593755","display_name":"Qi Song","orcid":"https://orcid.org/0009-0007-5833-3210"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Song","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056495776","display_name":"Xinyuan Qian","orcid":"https://orcid.org/0000-0002-9511-6713"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xinyuan Qian","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118911","display_name":"META Group","ror":"https://ror.org/027ng0s03","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210118911"]},{"id":"https://openalex.org/I4210140397","display_name":"Metrica (United States)","ror":"https://ror.org/031ffw737","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140397"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["Meta,United States","Meta, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta,United States","institution_ids":["https://openalex.org/I4210118911","https://openalex.org/I4210140397"]},{"raw_affiliation_string":"Meta, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996399998664856,"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":0.7667211890220642},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.71584552526474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6566588878631592},{"id":"https://openalex.org/keywords/ripple","display_name":"Ripple","score":0.5973713994026184},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5661077499389648},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5468825697898865},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5044106245040894},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4131767749786377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3082083463668823},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.127081036567688},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10064777731895447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667211890220642},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.71584552526474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6566588878631592},{"id":"https://openalex.org/C2779599953","wikidata":"https://www.wikidata.org/wiki/Q1776117","display_name":"Ripple","level":3,"score":0.5973713994026184},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5661077499389648},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5468825697898865},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5044106245040894},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4131767749786377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3082083463668823},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.127081036567688},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10064777731895447},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1506438021","https://openalex.org/W1897240248","https://openalex.org/W1976489750","https://openalex.org/W2038484192","https://openalex.org/W2069681747","https://openalex.org/W2144404214","https://openalex.org/W2159202424","https://openalex.org/W2219249508","https://openalex.org/W2291877678","https://openalex.org/W2396174604","https://openalex.org/W2516001803","https://openalex.org/W2539238457","https://openalex.org/W2792764867","https://openalex.org/W2897371647","https://openalex.org/W2914067823","https://openalex.org/W2950962438","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2964302946","https://openalex.org/W3015468748","https://openalex.org/W3016129867","https://openalex.org/W3017350693","https://openalex.org/W3026111682","https://openalex.org/W3095820034","https://openalex.org/W3097945073","https://openalex.org/W3106298483","https://openalex.org/W3147539069","https://openalex.org/W3163652268","https://openalex.org/W3197822518","https://openalex.org/W3214515055","https://openalex.org/W4295934635","https://openalex.org/W4296069339","https://openalex.org/W4312271884","https://openalex.org/W4385245566","https://openalex.org/W6639532686","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6749825310","https://openalex.org/W6770018571","https://openalex.org/W6776048684"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W2231565466","https://openalex.org/W3043214604","https://openalex.org/W1505346162"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,46,120,141,158],"Transformer":[3],"represents":[4],"a":[5,52,95,113],"recent":[6],"success":[7],"in":[8,94,156],"speech":[9,27,47,59,125,159],"enhancement.":[10],"However,":[11],"as":[12],"its":[13,90],"core":[14],"component,":[15],"self-attention":[16,57],"suffers":[17],"from":[18],"quadratic":[19],"complexity,":[20],"which":[21,64],"is":[22],"computationally":[23],"prohibited":[24],"for":[25,58,71,124],"long":[26],"recordings.":[28],"Moreover,":[29],"it":[30],"allows":[31],"each":[32,85],"time":[33,39],"frame":[34,86],"to":[35,37,83,87,89,107],"attend":[36,88],"all":[38],"frames,":[40],"neglecting":[41],"the":[42,105,109,118,138,142],"strong":[43],"local":[44,72,80],"correlations":[45],"signals.":[48],"This":[49],"study":[50],"presents":[51],"simple":[53],"yet":[54],"effective":[55],"sparse":[56],"enhancement,":[60],"called":[61],"ripple":[62,122,143],"attention,":[63,151],"simultaneously":[65],"performs":[66],"fine-":[67],"and":[68,73,152,161],"coarse-grained":[69],"modeling":[70],"global":[74,110],"dependencies,":[75],"respectively.":[76],"Specifically,":[77],"we":[78],"employ":[79],"band":[81],"attention":[82,103,123,144,154],"enable":[84],"closest":[91],"neighbor":[92],"frames":[93],"window":[96,106],"at":[97,112],"fine":[98],"granularity,":[99],"while":[100],"employing":[101],"dilated":[102],"outside":[104],"model":[108],"dependencies":[111],"coarse":[114],"granularity.":[115],"We":[116],"evaluate":[117],"efficacy":[119],"our":[121],"enhancement":[126],"on":[127],"two":[128],"commonly":[129],"used":[130],"training":[131],"objectives.":[132],"Extensive":[133],"experimental":[134],"results":[135],"consistently":[136],"confirm":[137],"superior":[139],"performance":[140],"design":[145],"over":[146],"standard":[147],"full":[148],"self-attention,":[149],"blockwise":[150],"dual-path":[153],"(Sep-Former)":[155],"terms":[157],"quality":[160],"intelligibility.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}