{"id":"https://openalex.org/W4396919231","doi":"https://doi.org/10.1145/3659598","title":"Sensing to Hear through Memory","display_name":"Sensing to Hear through Memory","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4396919231","doi":"https://doi.org/10.1145/3659598"},"language":"en","primary_location":{"id":"doi:10.1145/3659598","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659598","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3659598","source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3659598","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100401577","display_name":"Qian Zhang","orcid":"https://orcid.org/0000-0001-7708-8694"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0001-7708-8694","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ke Liu","orcid":"https://orcid.org/0009-0003-2347-1796"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0009-0003-2347-1796","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391426","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0001-8444-1636"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0001-8444-1636","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.1262,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75700365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"8","issue":"2","first_page":"1","last_page":"31"},"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8084162473678589},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6597573757171631},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6556932926177979},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6221062541007996},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4723856449127197},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45119708776474},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.45081764459609985},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.42136186361312866},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4192701280117035},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4104241728782654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34271439909935},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.29351621866226196},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08473607897758484},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07980617880821228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084162473678589},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6597573757171631},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6556932926177979},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6221062541007996},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4723856449127197},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45119708776474},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.45081764459609985},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.42136186361312866},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4192701280117035},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4104241728782654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34271439909935},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.29351621866226196},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08473607897758484},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07980617880821228},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3659598","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659598","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3659598","source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3659598","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659598","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3659598","source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3233741960","display_name":null,"funder_award_id":"62102245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396919231.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W1882423120","https://openalex.org/W2044893557","https://openalex.org/W2063383561","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2096779346","https://openalex.org/W2127851351","https://openalex.org/W2128653836","https://openalex.org/W2163835077","https://openalex.org/W2169744398","https://openalex.org/W2221409856","https://openalex.org/W2625581252","https://openalex.org/W2726515241","https://openalex.org/W2794782869","https://openalex.org/W2808631503","https://openalex.org/W2912868098","https://openalex.org/W2913618081","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2963448850","https://openalex.org/W2973062255","https://openalex.org/W2977115923","https://openalex.org/W3010673682","https://openalex.org/W3024869864","https://openalex.org/W3026815601","https://openalex.org/W3096028031","https://openalex.org/W3097945073","https://openalex.org/W3140645045","https://openalex.org/W3144915432","https://openalex.org/W3147539069","https://openalex.org/W3160085755","https://openalex.org/W3161865163","https://openalex.org/W3163978602","https://openalex.org/W3175593095","https://openalex.org/W3203789665","https://openalex.org/W3206706278","https://openalex.org/W3213107273","https://openalex.org/W3217415709","https://openalex.org/W4200186631","https://openalex.org/W4200482297","https://openalex.org/W4220710272","https://openalex.org/W4224319127","https://openalex.org/W4246270042","https://openalex.org/W4285795303","https://openalex.org/W4289665794","https://openalex.org/W4294892047","https://openalex.org/W4396919354","https://openalex.org/W6610654676"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W627697492"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,24,72,123,140],"on":[2,172],"mobile":[3],"devices":[4],"is":[5,48,109,155],"a":[6,32,58,86,132],"very":[7],"challenging":[8],"task":[9],"due":[10],"to":[11,29,89,111,119,136,163],"the":[12,64,75,91,96,99,106,113,139,146,149,152,165,173,191],"complex":[13],"environmental":[14],"noises.":[15],"Recent":[16],"works":[17],"using":[18],"lip-induced":[19],"ultrasound":[20,67,92,102,114,127],"signals":[21],"for":[22,69],"speech":[23,71,122],"open":[25],"up":[26],"new":[27],"possibilities":[28],"solve":[30],"such":[31],"problem.":[33],"However,":[34],"these":[35],"multi-modal":[36,70,121],"methods":[37,187],"cannot":[38],"be":[39],"used":[40],"in":[41],"many":[42],"scenarios":[43],"where":[44],"ultrasound-based":[45],"lip":[46],"sensing":[47],"unreliable":[49],"or":[50],"completely":[51],"absent.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,130],"propose":[57],"novel":[59],"paradigm":[60],"that":[61,179],"can":[62],"exploit":[63],"prior":[65],"learned":[66],"knowledge":[68],"only":[73],"with":[74,185],"audio":[76,100,117],"input":[77,118],"and":[78,94,101,168,188],"an":[79,159],"additional":[80],"pre-enrollment":[81],"speaker":[82,133],"embedding.":[83],"We":[84,157],"design":[85],"memory":[87,93,107],"network":[88,108],"store":[90],"learn":[95],"interrelationship":[97],"between":[98],"modality.":[103],"During":[104],"inference,":[105],"able":[110],"recall":[112],"representations":[115],"from":[116],"achieve":[120],"without":[124],"needing":[125],"real":[126],"signals.":[128],"Moreover,":[129],"introduce":[131],"embedding":[134],"module":[135],"further":[137],"boost":[138],"performance":[141,184],"as":[142,144],"well":[143],"avoid":[145],"degradation":[147],"of":[148],"recalling":[150],"when":[151],"noise":[153],"level":[154],"high.":[156],"adopt":[158],"end-to-end":[160],"multi-task":[161],"manner":[162],"train":[164],"proposed":[166],"framework":[167],"perform":[169],"extensive":[170],"evaluations":[171],"collected":[174],"dataset.":[175],"The":[176],"results":[177],"show":[178],"our":[180],"method":[181],"yields":[182],"comparable":[183],"audio-ultrasound":[186],"significantly":[189],"outperforms":[190],"audio-only":[192],"methods.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}