{"id":"https://openalex.org/W3008245519","doi":"https://doi.org/10.1109/icspcs47537.2019.9008724","title":"Untethered Distant Speech-to-Text Transcription Using Arrays of Directional Microphones","display_name":"Untethered Distant Speech-to-Text Transcription Using Arrays of Directional Microphones","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008245519","doi":"https://doi.org/10.1109/icspcs47537.2019.9008724","mag":"3008245519"},"language":"en","primary_location":{"id":"doi:10.1109/icspcs47537.2019.9008724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcs47537.2019.9008724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 13th International Conference on Signal Processing and Communication Systems (ICSPCS)","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/A5080123776","display_name":"Matthew Trinkle","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Matthew Trinkle","raw_affiliation_strings":["Department of Electrical Electronic Engineering, The University of Adelaide, Adelaide, SA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Electronic Engineering, The University of Adelaide, Adelaide, SA","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054038307","display_name":"Ahmad Hashemi-Sakhtsari","orcid":null},"institutions":[{"id":"https://openalex.org/I1303474014","display_name":"Defence Science and Technology Group","ror":"https://ror.org/05ddrvt52","country_code":"AU","type":"government","lineage":["https://openalex.org/I1303474014","https://openalex.org/I2801453606","https://openalex.org/I3139952251"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ahmad Hashemi-Sakhtsari","raw_affiliation_strings":["Language Technology and Cognition Group, Intelligence, Surveillance and Space Division, Defence Science and Technology Group, Edinburgh, SA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology and Cognition Group, Intelligence, Surveillance and Space Division, Defence Science and Technology Group, Edinburgh, SA","institution_ids":["https://openalex.org/I1303474014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.18808205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","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":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":0.9991000294685364,"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":0.9976000189781189,"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/microphone","display_name":"Microphone","score":0.7677303552627563},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7073987722396851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6836764812469482},{"id":"https://openalex.org/keywords/directivity","display_name":"Directivity","score":0.5788174271583557},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5157890319824219},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.47351837158203125},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.468900591135025},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43660467863082886},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4289172291755676},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4285227656364441},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.37231752276420593},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.3392997980117798},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.1623338758945465},{"id":"https://openalex.org/keywords/antenna","display_name":"Antenna (radio)","score":0.1572994589805603},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.14475631713867188},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11750108003616333},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10290279984474182}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7677303552627563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7073987722396851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6836764812469482},{"id":"https://openalex.org/C189039984","wikidata":"https://www.wikidata.org/wiki/Q8225412","display_name":"Directivity","level":3,"score":0.5788174271583557},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5157890319824219},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.47351837158203125},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.468900591135025},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43660467863082886},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4289172291755676},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4285227656364441},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.37231752276420593},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.3392997980117798},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.1623338758945465},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.1572994589805603},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.14475631713867188},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11750108003616333},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10290279984474182}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcs47537.2019.9008724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcs47537.2019.9008724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 13th International Conference on Signal Processing and Communication Systems (ICSPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W1572587302","https://openalex.org/W1982728343","https://openalex.org/W2061074721","https://openalex.org/W2066218102","https://openalex.org/W2129501075","https://openalex.org/W2170222430","https://openalex.org/W2539797148","https://openalex.org/W2582368098","https://openalex.org/W2889367162","https://openalex.org/W2891984996","https://openalex.org/W2897977894","https://openalex.org/W2947942791","https://openalex.org/W2962866211","https://openalex.org/W4206633762","https://openalex.org/W6728770099","https://openalex.org/W6754780805"],"related_works":["https://openalex.org/W2380771148","https://openalex.org/W2348931051","https://openalex.org/W2538903081","https://openalex.org/W2389562147","https://openalex.org/W4386746628","https://openalex.org/W2294333436","https://openalex.org/W2109356272","https://openalex.org/W4286233499","https://openalex.org/W2379497378","https://openalex.org/W2132495960"],"abstract_inverted_index":{"This":[0],"paper":[1,73],"considers":[2],"distant":[3,41],"speech":[4,34,107],"recognition":[5],"in":[6,19,71,80],"meeting":[7],"rooms":[8],"where":[9],"the":[10,16,43,58],"microphone":[11,68,83,115],"cannot":[12],"be":[13,54],"placed":[14,55],"on":[15],"table":[17],"directly":[18],"front":[20],"of":[21,38,48],"a":[22,106],"speaker.":[23],"Two":[24],"solutions":[25],"are":[26,62],"considered":[27,64],"for":[28,33],"obtaining":[29],"sufficient":[30],"audio":[31],"quality":[32],"recognition:":[35],"an":[36,46,81],"array":[37,47],"shotgun":[39],"microphones":[40,51,61],"from":[42,105],"speakers":[44],"and":[45,100],"hanging":[49],"(overhead)":[50],"which":[52],"can":[53],"closer":[56],"to":[57,67,86,94],"speakers.":[59],"Shotgun":[60],"typically":[63],"as":[65,78],"alternatives":[66],"arrays,":[69],"but":[70],"this":[72],"we":[74],"consider":[75],"their":[76,87],"use":[77],"elements":[79],"actual":[82],"array.":[84],"Due":[85],"high":[88],"directivity":[89],"they":[90],"provide":[91],"improved":[92],"Signal":[93],"Noise":[95],"Ratio":[96],"(SNR),":[97],"less":[98],"distortion":[99],"higher":[101],"word":[102],"accuracy":[103],"rate":[104],"recogniser":[108],"than":[109],"arrays":[110],"using":[111],"standard":[112],"gooseneck":[113],"cardioid":[114],"elements.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
