{"id":"https://openalex.org/W2994168567","doi":"https://doi.org/10.1109/wimob.2019.8923157","title":"Communications using a speech-to-text-to-speech pipeline","display_name":"Communications using a speech-to-text-to-speech pipeline","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2994168567","doi":"https://doi.org/10.1109/wimob.2019.8923157","mag":"2994168567"},"language":"en","primary_location":{"id":"doi:10.1109/wimob.2019.8923157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wimob.2019.8923157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)","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/A5012717437","display_name":"Rafael Dantas Lero","orcid":null},"institutions":[{"id":"https://openalex.org/I230495080","display_name":"University of Limerick","ror":"https://ror.org/00a0n9e72","country_code":"IE","type":"education","lineage":["https://openalex.org/I230495080"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Rafael Dantas Lero","raw_affiliation_strings":["University of Limerick, Limerick, Ireland"],"affiliations":[{"raw_affiliation_string":"University of Limerick, Limerick, Ireland","institution_ids":["https://openalex.org/I230495080"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109473268","display_name":"Chris Exton","orcid":"https://orcid.org/0000-0003-3587-2821"},"institutions":[{"id":"https://openalex.org/I230495080","display_name":"University of Limerick","ror":"https://ror.org/00a0n9e72","country_code":"IE","type":"education","lineage":["https://openalex.org/I230495080"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Chris Exton","raw_affiliation_strings":["Lero University of Limerick, Limerick, Ireland"],"affiliations":[{"raw_affiliation_string":"Lero University of Limerick, Limerick, Ireland","institution_ids":["https://openalex.org/I230495080"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027730192","display_name":"Andrew Le Gear","orcid":"https://orcid.org/0000-0002-0886-7683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Le Gear","raw_affiliation_strings":["Nexus Innovation Centre, Horizon Globex Ltd., Limerick, Ireland"],"affiliations":[{"raw_affiliation_string":"Nexus Innovation Centre, Horizon Globex Ltd., Limerick, Ireland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012717437"],"corresponding_institution_ids":["https://openalex.org/I230495080"],"apc_list":null,"apc_paid":null,"fwci":0.8401,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.80991292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9973999857902527,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8320063352584839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7490456104278564},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7181218266487122},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.694640576839447},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6573803424835205},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.6096886992454529},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5782907009124756},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.5701237916946411},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5689957141876221},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5640729069709778},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.5237429141998291},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5231731534004211},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41197073459625244},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3312644362449646},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.12723931670188904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320063352584839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7490456104278564},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7181218266487122},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.694640576839447},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6573803424835205},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.6096886992454529},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5782907009124756},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.5701237916946411},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5689957141876221},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5640729069709778},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.5237429141998291},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5231731534004211},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41197073459625244},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3312644362449646},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.12723931670188904},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wimob.2019.8923157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wimob.2019.8923157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W183182694","https://openalex.org/W193250652","https://openalex.org/W1520449809","https://openalex.org/W1527538280","https://openalex.org/W1647671624","https://openalex.org/W1922655562","https://openalex.org/W2024089300","https://openalex.org/W2084609288","https://openalex.org/W2154360824","https://openalex.org/W2461356623","https://openalex.org/W2798943951","https://openalex.org/W2979776555","https://openalex.org/W2999282340","https://openalex.org/W3163240479","https://openalex.org/W6607539543","https://openalex.org/W6631166905","https://openalex.org/W6636915900","https://openalex.org/W6640090968","https://openalex.org/W6682998932","https://openalex.org/W6718400314","https://openalex.org/W6768908985"],"related_works":["https://openalex.org/W137020845","https://openalex.org/W4319347033","https://openalex.org/W1542588102","https://openalex.org/W2020464095","https://openalex.org/W2151333624","https://openalex.org/W1890431648","https://openalex.org/W1572861854","https://openalex.org/W1987001738","https://openalex.org/W1968776176","https://openalex.org/W1591426470"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,63,119],"discuss":[4],"the":[5,36,66,74,82,108,111,124,129,134,138,160,170,174],"feasibility":[6],"of":[7,18,38,69,81,110,162],"using":[8,39],"an":[9],"automated":[10],"speech-to-speech":[11],"pipeline":[12],"to":[13,92,106,114,128,153],"encode":[14],"voice":[15,20,45,116,172],"samples":[16,85],"instead":[17],"regular":[19],"codecs,":[21],"in":[22,89],"situations":[23],"that":[24],"require":[25],"high":[26,30],"data":[27],"compression":[28],"with":[29],"packet":[31,101],"loss":[32],"scenarios.":[33],"To":[34],"analyse":[35],"advantages":[37],"a":[40,44,48,52,59,90,157,166],"speech-to-text":[41,112,155],"transcription":[42],"as":[43,51,156,159],"encoder":[46],"and":[47,54,99,140,173],"text-to-speech":[49],"synthesis":[50],"decoder":[53],"compare":[55,107],"it":[56,149],"against":[57],"standard":[58,115],"PCM":[60,83],"A-law":[61],"codec,":[62,158],"have":[64,120],"measured":[65],"error":[67],"rate":[68],"user-transcribed":[70],"sentences":[71,139],"based":[72],"on":[73],"Semantically":[75],"Unpredictable":[76],"Sentences":[77],"(SUS)":[78],"test.":[79],"Some":[80],"speech":[84],"were":[86,104,127],"also":[87,141],"played":[88],"way":[91],"simulate":[93],"poor":[94],"network":[95],"conditions,":[96],"specifically":[97],"5%":[98],"10%":[100],"loss.":[102],"These":[103],"added":[105],"performance":[109],"method":[113],"codecs.":[117],"Additionally,":[118],"evaluated":[121],"how":[122],"similar":[123],"transcribed":[125],"messages":[126],"ground":[130],"truth":[131],"by":[132],"measuring":[133],"Levenshtein":[135],"distance":[136],"between":[137,169],"their":[142],"Double":[143],"Metaphone":[144],"phonetic":[145],"representations.":[146],"We":[147],"conclude":[148],"may":[150],"be":[151],"feasible":[152],"use":[154],"results":[161],"do":[163],"not":[164],"show":[165],"significant":[167],"difference":[168],"synthesised":[171],"real":[175],"voice.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}