{"id":"https://openalex.org/W4408356748","doi":"https://doi.org/10.1109/icassp49660.2025.10889875","title":"Towards Sub-millisecond Latency Real-Time Speech Enhancement Models on Hearables","display_name":"Towards Sub-millisecond Latency Real-Time Speech Enhancement Models on Hearables","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356748","doi":"https://doi.org/10.1109/icassp49660.2025.10889875"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5014474985","display_name":"Artem Dementyev","orcid":"https://orcid.org/0009-0001-2826-1099"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Artem Dementyev","raw_affiliation_strings":["Google DeepMind"],"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001022750","display_name":"Chandan K. Reddy","orcid":"https://orcid.org/0000-0003-2839-3662"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandan K. A. Reddy","raw_affiliation_strings":["Google Platforms & Devices"],"affiliations":[{"raw_affiliation_string":"Google Platforms & Devices","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Scott Wisdom","raw_affiliation_strings":["Google DeepMind"],"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018864602","display_name":"Navin Chatlani","orcid":"https://orcid.org/0000-0001-5844-1667"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Navin Chatlani","raw_affiliation_strings":["Google Platforms & Devices"],"affiliations":[{"raw_affiliation_string":"Google Platforms & Devices","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google DeepMind"],"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026382065","display_name":"Richard F. Lyon","orcid":"https://orcid.org/0000-0003-2348-811X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard F. Lyon","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014474985"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":3.122,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89736245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"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":0.9984999895095825,"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":0.9984999895095825,"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":0.972599983215332,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9455000162124634,"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/millisecond","display_name":"Millisecond","score":0.8227514028549194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557456493377686},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6867970824241638},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.526616632938385},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08023881912231445},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07645925879478455}],"concepts":[{"id":"https://openalex.org/C60327585","wikidata":"https://www.wikidata.org/wiki/Q723733","display_name":"Millisecond","level":2,"score":0.8227514028549194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557456493377686},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6867970824241638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.526616632938385},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08023881912231445},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07645925879478455},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1728888090","https://openalex.org/W1934189836","https://openalex.org/W2041944559","https://openalex.org/W2062461584","https://openalex.org/W2101045344","https://openalex.org/W2963122961","https://openalex.org/W2963189033","https://openalex.org/W2963902628","https://openalex.org/W2964058413","https://openalex.org/W3015199127","https://openalex.org/W3028019732","https://openalex.org/W3161480375","https://openalex.org/W3174108421","https://openalex.org/W3197042120","https://openalex.org/W4226372244","https://openalex.org/W4292387427","https://openalex.org/W4311187069","https://openalex.org/W4385822774","https://openalex.org/W6629956514","https://openalex.org/W6746278845"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2368158069","https://openalex.org/W2129058931","https://openalex.org/W2074671889","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2489894763"],"abstract_inverted_index":{"Low":[0],"latency":[1,19,44,110,136],"models":[2],"are":[3],"critical":[4],"for":[5,21],"real-time":[6],"speech":[7,28],"enhancement":[8,29],"applications,":[9],"such":[10],"as":[11],"hearing":[12],"aids":[13],"and":[14,106,137,145],"hearables.":[15,148],"However,":[16],"the":[17,143],"sub-millisecond":[18],"space":[20],"resource-constrained":[22],"hearables":[23],"remains":[24],"underexplored.":[25],"We":[26,77,126],"demonstrate":[27],"using":[30],"a":[31,52,57,68,79,91,96,107,118,132],"computationally":[32],"efficient":[33],"minimum-phase":[34],"FIR":[35,88],"filter,":[36],"enabling":[37],"sample-by-sample":[38],"processing":[39],"to":[40,48,86,141],"achieve":[41],"mean":[42,58,108],"algorithmic":[43],"of":[45,60,71,83,111,135,147],"0.32":[46],"ms":[47],"1.25":[49],"ms.":[50,113],"With":[51],"single":[53],"microphone,":[54],"we":[55,116],"observe":[56],"SI-SDRi":[59],"4.1":[61],"dB.":[62],"The":[63],"approach":[64],"shows":[65],"generalization":[66],"with":[67,103,120],"DNSMOS":[69],"increase":[70],"0.2":[72],"on":[73,95],"unseen":[74],"audio":[75],"recordings.":[76],"use":[78],"lightweight":[80],"LSTM-based":[81],"model":[82],"626k":[84],"parameters":[85],"generate":[87],"taps.":[89],"Using":[90],"real":[92],"hardware":[93],"implementation":[94],"low-power":[97],"DSP,":[98],"our":[99],"system":[100],"can":[101,138],"run":[102],"376":[104],"MIPS":[105],"end-to-end":[109],"3.35":[112],"In":[114],"addition,":[115],"provide":[117],"comparison":[119],"existing":[121],"low-latency":[122],"spectral":[123],"masking":[124],"techniques.":[125],"hope":[127],"this":[128],"work":[129],"will":[130],"enable":[131],"better":[133],"understanding":[134],"be":[139],"used":[140],"improve":[142],"comfort":[144],"usability":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}