{"id":"https://openalex.org/W4406264865","doi":"https://doi.org/10.1109/wimob61911.2024.10770530","title":"Evaluating Text-to-Speech and Audio Codec Performance for Voice Communication in Resource-Constrained Networks","display_name":"Evaluating Text-to-Speech and Audio Codec Performance for Voice Communication in Resource-Constrained Networks","publication_year":2024,"publication_date":"2024-10-21","ids":{"openalex":"https://openalex.org/W4406264865","doi":"https://doi.org/10.1109/wimob61911.2024.10770530"},"language":"en","primary_location":{"id":"doi:10.1109/wimob61911.2024.10770530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wimob61911.2024.10770530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 20th 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/A5012706984","display_name":"Batuhan Mekiker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Batuhan Mekiker","raw_affiliation_strings":["Beartooth Radio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beartooth Radio","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010395542","display_name":"Mike P. Wittie","orcid":"https://orcid.org/0000-0002-3752-2430"},"institutions":[{"id":"https://openalex.org/I23732399","display_name":"Montana State University","ror":"https://ror.org/02w0trx84","country_code":"US","type":"education","lineage":["https://openalex.org/I23732399","https://openalex.org/I4210126032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike P. Wittie","raw_affiliation_strings":["Montana State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montana State University","institution_ids":["https://openalex.org/I23732399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76041495,"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":"312","last_page":"317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.970300018787384,"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/T12031","display_name":"Speech and dialogue systems","score":0.970300018787384,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9122999906539917,"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":0.8297244310379028},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.8250936269760132},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.8109447360038757},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6589901447296143},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6351590156555176},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5914580225944519},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.5368829965591431},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4965100884437561},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.42850661277770996},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38703516125679016},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2530972957611084},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16920793056488037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297244310379028},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.8250936269760132},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8109447360038757},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6589901447296143},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6351590156555176},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5914580225944519},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.5368829965591431},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4965100884437561},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.42850661277770996},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38703516125679016},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2530972957611084},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16920793056488037}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wimob61911.2024.10770530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wimob61911.2024.10770530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 20th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarworks.montana.edu:1/19544","is_oa":false,"landing_page_url":"https://scholarworks.montana.edu/handle/1/19544","pdf_url":null,"source":{"id":"https://openalex.org/S4306402563","display_name":"Montana State University ScholarWorks (Montana State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I23732399","host_organization_name":"Montana State University","host_organization_lineage":["https://openalex.org/I23732399"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2159307410","https://openalex.org/W1601770773","https://openalex.org/W137020845","https://openalex.org/W2106874932","https://openalex.org/W1542588102","https://openalex.org/W1911859126","https://openalex.org/W2151333624","https://openalex.org/W2020464095","https://openalex.org/W2289505355","https://openalex.org/W1578591928"],"abstract_inverted_index":{"Voice":[0],"communications":[1,33],"are":[2],"valued":[3],"for":[4,62],"their":[5,115],"ease":[6],"of":[7,31,46],"use":[8],"and":[9,19,29,50,65,79,92,121],"the":[10,27,44,82,88,107],"rich":[11],"information":[12],"they":[13],"provide,":[14],"offering":[15],"an":[16],"immediate,":[17],"clear,":[18],"efficient":[20],"way":[21],"to":[22,110],"convey":[23],"messages.":[24],"However,":[25],"ensuring":[26],"clarity":[28,64],"reliability":[30],"voice":[32,63],"in":[34,57,72,90],"low-bandwidth":[35,58],"networks":[36],"poses":[37],"a":[38,96,100],"technical":[39],"challenge.":[40],"This":[41],"research":[42],"explores":[43],"efficacy":[45],"Text-to-Speech":[47],"(TTS)":[48],"models":[49],"vocoder":[51],"combinations":[52],"versus":[53],"traditional":[54],"audio":[55,70,77,119],"codecs":[56,71],"networks,":[59],"highlighting":[60],"considerations":[61],"network":[66,122],"resource":[67],"management.":[68],"Traditional":[69],"bandwidth-limited":[73],"environments":[74],"often":[75],"compromise":[76],"quality":[78,120],"reliability.":[80],"On":[81],"contrary,":[83],"TTS":[84],"models,":[85],"supported":[86],"by":[87],"advancements":[89],"deep":[91],"machine":[93],"learning,":[94],"present":[95],"potential":[97],"alternative.":[98],"Through":[99],"methodical":[101],"comparison":[102],"using":[103],"various":[104],"evaluation":[105],"metrics,":[106],"study":[108],"aims":[109],"offer":[111],"valuable":[112],"insights":[113],"into":[114],"comparative":[116],"impacts":[117],"on":[118],"behavior.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}