{"id":"https://openalex.org/W4402349570","doi":"https://doi.org/10.1145/3678515","title":"StethoSpeech: Speech Generation Through a Clinical Stethoscope Attached to the Skin","display_name":"StethoSpeech: Speech Generation Through a Clinical Stethoscope Attached to the Skin","publication_year":2024,"publication_date":"2024-08-22","ids":{"openalex":"https://openalex.org/W4402349570","doi":"https://doi.org/10.1145/3678515"},"language":"en","primary_location":{"id":"doi:10.1145/3678515","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678515","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003211639","display_name":"Neil Shah","orcid":"https://orcid.org/0000-0002-7517-3673"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neil Shah","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India and TCS Research, Pune, Maharashtra, India"],"raw_orcid":"https://orcid.org/0000-0002-7517-3673","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India and TCS Research, Pune, Maharashtra, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092418416","display_name":"Neha Sahipjohn","orcid":"https://orcid.org/0009-0009-1101-8701"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neha Sahipjohn","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India"],"raw_orcid":"https://orcid.org/0009-0009-1101-8701","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088806439","display_name":"Vishal Tambrahalli","orcid":"https://orcid.org/0009-0008-1396-1106"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vishal Tambrahalli","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India"],"raw_orcid":"https://orcid.org/0009-0008-1396-1106","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089971631","display_name":"Ramanathan Subramanian","orcid":"https://orcid.org/0000-0001-9441-7074"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ramanathan Subramanian","raw_affiliation_strings":["University of Canberra, Bruce, Canberra, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9441-7074","affiliations":[{"raw_affiliation_string":"University of Canberra, Bruce, Canberra, Australia","institution_ids":["https://openalex.org/I188329596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067298540","display_name":"Vineet Gandhi","orcid":"https://orcid.org/0000-0001-8861-7731"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vineet Gandhi","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India"],"raw_orcid":"https://orcid.org/0000-0001-8861-7731","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5273,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8553955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"8","issue":"3","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7302410006523132},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6685352325439453},{"id":"https://openalex.org/keywords/stethoscope","display_name":"Stethoscope","score":0.4987754821777344},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.49728038907051086},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.4685291647911072},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4502068758010864},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31646788120269775},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15716463327407837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302410006523132},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6685352325439453},{"id":"https://openalex.org/C2779055095","wikidata":"https://www.wikidata.org/wiki/Q162339","display_name":"Stethoscope","level":2,"score":0.4987754821777344},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.49728038907051086},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.4685291647911072},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4502068758010864},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31646788120269775},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15716463327407837},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3678515","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678515","pdf_url":null,"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":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W68041361","https://openalex.org/W830267248","https://openalex.org/W1540787848","https://openalex.org/W1635512741","https://openalex.org/W1986593580","https://openalex.org/W1986910277","https://openalex.org/W1991169524","https://openalex.org/W1999209169","https://openalex.org/W2071431631","https://openalex.org/W2095026407","https://openalex.org/W2120605154","https://openalex.org/W2127141656","https://openalex.org/W2156060621","https://openalex.org/W2160800342","https://openalex.org/W2303272654","https://openalex.org/W2770785043","https://openalex.org/W2793257307","https://openalex.org/W2888796252","https://openalex.org/W2889413431","https://openalex.org/W2914304175","https://openalex.org/W2933138175","https://openalex.org/W2946200149","https://openalex.org/W2963341956","https://openalex.org/W2973049979","https://openalex.org/W2987496713","https://openalex.org/W3004196347","https://openalex.org/W3005302394","https://openalex.org/W3015356564","https://openalex.org/W3015465870","https://openalex.org/W3035626590","https://openalex.org/W3090484329","https://openalex.org/W3140429000","https://openalex.org/W3160728073","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4321009928","https://openalex.org/W4323322934","https://openalex.org/W4361763861","https://openalex.org/W4381786045","https://openalex.org/W4385574033","https://openalex.org/W4385823362","https://openalex.org/W4386076005","https://openalex.org/W4386566590","https://openalex.org/W4388821341","https://openalex.org/W4390872483","https://openalex.org/W4393171356"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"We":[0,91],"introduce":[1],"StethoSpeech,":[2],"a":[3,50,81,107],"silent":[4],"speech":[5,117],"interface":[6],"that":[7,122],"transforms":[8],"flesh-conducted":[9],"vibrations":[10,47],"behind":[11],"the":[12,72,77,88,96],"ear":[13],"into":[14],"speech.":[15],"This":[16],"innovation":[17],"is":[18],"designed":[19],"to":[20,144,148],"improve":[21],"social":[22],"interactions":[23],"for":[24,45,53,116],"those":[25],"with":[26,60],"voice":[27],"disorders,":[28],"and":[29,48,80,103,114,126,136,154],"furthermore":[30],"enable":[31],"discreet":[32],"public":[33],"communication.":[34],"Unlike":[35],"prior":[36],"efforts,":[37],"StethoSpeech":[38,123],"does":[39],"not":[40,150],"require":[41],"(a)":[42],"paired-speech":[43],"data":[44],"recorded":[46],"(b)":[49],"specialized":[51],"device":[52],"recording":[54],"vibrations,":[55],"as":[56],"it":[57],"can":[58],"work":[59],"an":[61],"off-the-shelf":[62],"clinical":[63],"stethoscope.":[64],"The":[65],"novelty":[66],"of":[67,76,111],"our":[68,104],"framework":[69],"lies":[70],"in":[71,87,157],"overall":[73],"design,":[74],"simulation":[75],"ground-truth":[78],"speech,":[79,128],"sequence-to-sequence":[82],"translation":[83],"network,":[84],"which":[85],"works":[86],"latent":[89],"space.":[90],"present":[92],"comprehensive":[93],"experiments":[94],"on":[95,133],"existing":[97,131],"CSTR":[98],"NAM":[99],"TIMIT":[100],"Plus":[101],"corpus":[102],"proposed":[105],"StethoText:":[106],"large-scale":[108],"synchronized":[109],"database":[110],"non-audible":[112],"murmur":[113],"text":[115],"research.":[118],"Our":[119],"results":[120],"show":[121],"provides":[124],"natural-sounding":[125],"intelligible":[127],"significantly":[129],"outperforming":[130],"methods":[132],"several":[134],"quantitative":[135],"qualitative":[137],"metrics.":[138],"Additionally,":[139],"we":[140],"showcase":[141],"its":[142,146,155],"capacity":[143],"extend":[145],"application":[147],"speakers":[149],"encountered":[151],"during":[152],"training":[153],"effectiveness":[156],"challenging,":[158],"noisy":[159],"environments.":[160],"Speech":[161],"samples":[162],"are":[163],"available":[164],"at":[165],"https://stethospeech.github.io/StethoSpeech/.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}