{"id":"https://openalex.org/W4387993513","doi":"https://doi.org/10.1145/3586182.3615789","title":"LiveLocalizer: Augmenting Mobile Speech-to-Text with Microphone Arrays, Optimized Localization and Beamforming","display_name":"LiveLocalizer: Augmenting Mobile Speech-to-Text with Microphone Arrays, Optimized Localization and Beamforming","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4387993513","doi":"https://doi.org/10.1145/3586182.3615789"},"language":"en","primary_location":{"id":"doi:10.1145/3586182.3615789","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3586182.3615789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology","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/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":true,"raw_author_name":"Artem Dementyev","raw_affiliation_strings":["Google Research, United States"],"raw_orcid":"https://orcid.org/0009-0001-2826-1099","affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046671967","display_name":"Dimitri Kanevsky","orcid":null},"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":"Dimitri Kanevsky","raw_affiliation_strings":["Google Research, United States"],"raw_orcid":"https://orcid.org/0000-0001-5316-8593","affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108597","display_name":"Samuel Yang","orcid":"https://orcid.org/0000-0003-2460-6456"},"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":"Samuel Yang","raw_affiliation_strings":["Google Research, United States"],"raw_orcid":"https://orcid.org/0000-0003-2460-6456","affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059356940","display_name":"Mathieu Parvaix","orcid":null},"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":"Mathieu Parvaix","raw_affiliation_strings":["Google Research, United States"],"raw_orcid":"https://orcid.org/0009-0009-4544-8304","affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022048907","display_name":"Chiong Ching Lai","orcid":"https://orcid.org/0009-0005-0302-1602"},"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":"Chiong Lai","raw_affiliation_strings":["Google Research, United States"],"raw_orcid":"https://orcid.org/0009-0005-0302-1602","affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093135949","display_name":"Alex Olwal","orcid":"https://orcid.org/0000-0003-2578-3403"},"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":"Alex Olwal","raw_affiliation_strings":["Google Research, United States"],"raw_orcid":"https://orcid.org/0000-0003-2578-3403","affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014474985"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.381,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57439425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976999759674072,"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/T12031","display_name":"Speech and dialogue systems","score":0.9973999857902527,"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":0.7625615000724792},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6986066102981567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6961957812309265},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6869175434112549},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5837392210960388},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5645859241485596},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4708927273750305},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45520758628845215},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3924848735332489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32466182112693787},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.11027517914772034},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10971477627754211},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08789578080177307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7625615000724792},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6986066102981567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6961957812309265},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6869175434112549},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5837392210960388},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5645859241485596},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4708927273750305},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45520758628845215},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3924848735332489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32466182112693787},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.11027517914772034},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10971477627754211},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08789578080177307},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3586182.3615789","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3586182.3615789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2020057089","https://openalex.org/W2046317813","https://openalex.org/W2135131618","https://openalex.org/W2161071682","https://openalex.org/W2161254115","https://openalex.org/W2526335939","https://openalex.org/W2769353366","https://openalex.org/W3032066720","https://openalex.org/W3097499461"],"related_works":["https://openalex.org/W2380771148","https://openalex.org/W2348931051","https://openalex.org/W2132495960","https://openalex.org/W2120771489","https://openalex.org/W2538903081","https://openalex.org/W2389562147","https://openalex.org/W2109356272","https://openalex.org/W4386746628","https://openalex.org/W2051376034","https://openalex.org/W2294333436"],"abstract_inverted_index":{"Speech-to-text":[0],"capabilities":[1],"on":[2],"mobile":[3],"devices":[4],"have":[5],"proven":[6],"helpful":[7],"for":[8],"language":[9],"translation,":[10],"note-taking,":[11],"hearing":[12],"and":[13,16,39],"speech":[14,35],"accessibility,":[15],"meeting":[17],"transcripts.":[18],"However,":[19],"their":[20],"usefulness":[21],"is":[22,36],"constrained":[23],"by":[24],"being":[25],"unable":[26],"to":[27],"distinguish":[28],"between":[29],"multiple":[30],"speakers,":[31],"track":[32],"which":[33],"direction":[34],"coming":[37],"from,":[38],"provide":[40],"acceptable":[41],"performance":[42],"in":[43],"noisy":[44],"environments.":[45]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
