{"id":"https://openalex.org/W4402118929","doi":"https://doi.org/10.21437/interspeech.2024-1444","title":"Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds","display_name":"Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402118929","doi":"https://doi.org/10.21437/interspeech.2024-1444"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1444","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1444","pdf_url":"https://www.isca-archive.org/interspeech_2024/bae24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/bae24_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046330926","display_name":"Hanbin Bae","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hanbin Bae","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008290260","display_name":"Pavel Andreev","orcid":"https://orcid.org/0000-0001-9645-4418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavel Andreev","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034906389","display_name":"Azat Saginbaev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Azat Saginbaev","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091254085","display_name":"Nicholas Babaev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas Babaev","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073889412","display_name":"WonJun Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"WonJun Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082652105","display_name":"Hosang Sung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hosang Sung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052468556","display_name":"Hoon Young Cho","orcid":"https://orcid.org/0000-0002-6850-6580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoon-Young Cho","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5046330926"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7153,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68565379,"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":"647","last_page":"651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9987000226974487,"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/T10936","display_name":"Millimeter-Wave Propagation and Modeling","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.972000002861023,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/speech-enhancement","display_name":"Speech enhancement","score":0.80854731798172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.781865119934082},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6895067691802979},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6615148782730103},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5888397097587585},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5430180430412292},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.5004308223724365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49201056361198425},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4401002824306488},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.34184831380844116},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33115100860595703},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3156912922859192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2449702024459839},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14141568541526794},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1395728886127472},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11010760068893433}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.80854731798172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781865119934082},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6895067691802979},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6615148782730103},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5888397097587585},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5430180430412292},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.5004308223724365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49201056361198425},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4401002824306488},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34184831380844116},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33115100860595703},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3156912922859192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2449702024459839},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14141568541526794},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1395728886127472},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11010760068893433},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-1444","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1444","pdf_url":"https://www.isca-archive.org/interspeech_2024/bae24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.18705","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.18705","pdf_url":"https://arxiv.org/pdf/2409.18705","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-1444","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1444","pdf_url":"https://www.isca-archive.org/interspeech_2024/bae24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402118929.pdf","grobid_xml":"https://content.openalex.org/works/W4402118929.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W2072884270","https://openalex.org/W4252682934","https://openalex.org/W2089240210"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,60],"speech":[4,35,92],"enhancement":[5,36,93],"solution":[6,16],"tailored":[7],"for":[8,34],"true":[9],"wireless":[10],"stereo":[11],"(TWS)":[12],"earbuds":[13],"on-device":[14,47],"usage.The":[15],"was":[17],"specifically":[18],"designed":[19],"to":[20,58],"support":[21],"conversations":[22],"in":[23,38,91,98],"noisy":[24],"environments,":[25],"with":[26,96],"active":[27],"noise":[28],"cancellation":[29],"(ANC)":[30],"activated.The":[31],"primary":[32],"challenges":[33],"models":[37],"this":[39],"context":[40],"arise":[41],"from":[42],"computational":[43,105],"complexity":[44,106],"that":[45,51,97],"limits":[46],"usage":[48],"and":[49,76,84,107],"latency":[50],"must":[52],"be":[53],"less":[54],"than":[55],"3":[56],"ms":[57],"preserve":[59],"live":[61],"conversation.To":[62],"address":[63],"these":[64],"issues,":[65],"we":[66,87],"evaluated":[67],"several":[68],"crucial":[69],"design":[70,78],"elements,":[71],"including":[72],"the":[73,104],"network":[74],"architecture":[75],"domain,":[77],"of":[79],"loss":[80],"functions,":[81],"pruning":[82],"method,":[83],"hardware-specific":[85],"optimization.Consequently,":[86],"demonstrated":[88],"substantial":[89],"improvements":[90],"quality":[94],"compared":[95],"baseline":[99],"models,":[100],"while":[101],"simultaneously":[102],"reducing":[103],"algorithmic":[108],"latency.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
