{"id":"https://openalex.org/W4385822478","doi":"https://doi.org/10.21437/interspeech.2023-1084","title":"A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models","display_name":"A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822478","doi":"https://doi.org/10.21437/interspeech.2023-1084"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1084","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1084","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/A5058318424","display_name":"Pin-Jui Ku","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pin-Jui Ku","raw_affiliation_strings":["Georgia Institute of Technology, U.S.A"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, U.S.A","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["Georgia Institute of Technology, U.S.A"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, U.S.A","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]}],"countries":["IT","NO","US"],"is_corresponding":false,"raw_author_name":"Sabato Siniscalchi","raw_affiliation_strings":["Kore University of Enna, Italy","Georgia Institute of Technology, U.S.A","Norwegian University of Science and Technology, Norway"],"affiliations":[{"raw_affiliation_string":"Kore University of Enna, Italy","institution_ids":["https://openalex.org/I246010334"]},{"raw_affiliation_string":"Georgia Institute of Technology, U.S.A","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Norwegian University of Science and Technology, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, U.S.A"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, U.S.A","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058318424"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":2.8012,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91607829,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2453","last_page":"2457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.991599977016449,"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":0.974399983882904,"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/speech-enhancement","display_name":"Speech enhancement","score":0.7531111240386963},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.7456751465797424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6501938104629517},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46151942014694214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3648732602596283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3249335289001465},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.1328616738319397},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06399822235107422}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7531111240386963},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.7456751465797424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6501938104629517},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46151942014694214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3648732602596283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3249335289001465},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.1328616738319397},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06399822235107422},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-1084","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1084","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:iris.unipa.it:10447/637526","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/637526","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1815076433","https://openalex.org/W1897240248","https://openalex.org/W1936725236","https://openalex.org/W1968939597","https://openalex.org/W1969156340","https://openalex.org/W1976890732","https://openalex.org/W2031647436","https://openalex.org/W2044893557","https://openalex.org/W2053165762","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2126625374","https://openalex.org/W2128653836","https://openalex.org/W2130809717","https://openalex.org/W2135823751","https://openalex.org/W2149535104","https://openalex.org/W2162130745","https://openalex.org/W2188333210","https://openalex.org/W2757519008","https://openalex.org/W2760287881","https://openalex.org/W2891433113","https://openalex.org/W2949558265","https://openalex.org/W2949756029","https://openalex.org/W2952218014","https://openalex.org/W2963341071","https://openalex.org/W2998678989","https://openalex.org/W3015338123","https://openalex.org/W3096408984","https://openalex.org/W3097756030","https://openalex.org/W3097945073","https://openalex.org/W3098805155","https://openalex.org/W3131332223","https://openalex.org/W3209374680","https://openalex.org/W3212492847","https://openalex.org/W4221144097","https://openalex.org/W4221152471","https://openalex.org/W4287236406","https://openalex.org/W4289242435","https://openalex.org/W4307022632","https://openalex.org/W4372260519","https://openalex.org/W4375869120","https://openalex.org/W4380434618"],"related_works":["https://openalex.org/W2653598178","https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W2166831097","https://openalex.org/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W1986772939","https://openalex.org/W2618631492","https://openalex.org/W4375869276","https://openalex.org/W3129072390"],"abstract_inverted_index":{"We":[0,43],"propose":[1],"a":[2,63,78,116,133],"multi-dimensional":[3,27],"structured":[4],"state":[5],"space":[6],"(S4)":[7],"approach":[8],"to":[9,33],"speech":[10],"enhancement.":[11],"To":[12],"better":[13],"capture":[14],"the":[15,19,26,84,91,99,126],"spectral":[16],"dependencies":[17],"across":[18],"frequency":[20],"axis,":[21],"we":[22,129],"focus":[23],"on":[24,83,96],"modifying":[25],"S4":[28,58],"layer":[29,59,66],"with":[30,67,90,115,121],"whitening":[31],"transformation":[32],"build":[34],"new":[35],"small-footprint":[36],"models":[37],"that":[38],"also":[39],"achieve":[40],"good":[41],"performance.":[42],"explore":[44],"several":[45],"S4-based":[46,102],"deep":[47],"architectures":[48],"in":[49,107],"time":[50],"(T)":[51],"and":[52],"time-frequency":[53],"(TF)":[54],"domains.":[55],"The":[56],"2-D":[57],"can":[60,130],"be":[61],"considered":[62],"particular":[64],"convolutional":[65,80,97],"an":[68],"infinite":[69],"receptive":[70],"field":[71],"although":[72],"it":[73,110],"utilizes":[74],"fewer":[75],"parameters":[76],"than":[77],"conventional":[79,92],"layer.":[81],"Evaluated":[82],"VoiceBank-DEMAND":[85],"data":[86,122],"set,":[87],"when":[88],"compared":[89],"U-net":[93],"model":[94,103,127],"based":[95],"layers,":[98],"proposed":[100],"TF-domain":[101],"is":[104],"78.6%":[105],"smaller":[106],"size,":[108,128],"yet":[109],"still":[111],"achieves":[112],"competitive":[113],"results":[114],"PESQ":[117,134],"score":[118,135],"of":[119,136],"3.15":[120],"augmentation.":[123],"By":[124],"increasing":[125],"even":[131],"reach":[132],"3.18.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}