{"id":"https://openalex.org/W4403510204","doi":"https://doi.org/10.1109/access.2024.3482359","title":"A Bitrate-Scalable Variational Recurrent Mel-Spectrogram Coder for Real-Time Resynthesis-Based Speech Coding","display_name":"A Bitrate-Scalable Variational Recurrent Mel-Spectrogram Coder for Real-Time Resynthesis-Based Speech Coding","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403510204","doi":"https://doi.org/10.1109/access.2024.3482359"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3482359","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3482359","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3482359","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114312920","display_name":"Benjamin Stahl","orcid":"https://orcid.org/0000-0001-6446-0039"},"institutions":[{"id":"https://openalex.org/I317320687","display_name":"University of Music and Performing Arts Graz","ror":"https://ror.org/0541v4g57","country_code":"AT","type":"education","lineage":["https://openalex.org/I317320687"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Benjamin Stahl","raw_affiliation_strings":["Institute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, Austria"],"raw_orcid":"https://orcid.org/0000-0001-6446-0039","affiliations":[{"raw_affiliation_string":"Institute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, Austria","institution_ids":["https://openalex.org/I317320687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003370892","display_name":"Simon Windtner","orcid":null},"institutions":[{"id":"https://openalex.org/I317320687","display_name":"University of Music and Performing Arts Graz","ror":"https://ror.org/0541v4g57","country_code":"AT","type":"education","lineage":["https://openalex.org/I317320687"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Simon Windtner","raw_affiliation_strings":["Institute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, Austria","institution_ids":["https://openalex.org/I317320687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087260049","display_name":"Alois Sontacchi","orcid":"https://orcid.org/0009-0008-9205-209X"},"institutions":[{"id":"https://openalex.org/I317320687","display_name":"University of Music and Performing Arts Graz","ror":"https://ror.org/0541v4g57","country_code":"AT","type":"education","lineage":["https://openalex.org/I317320687"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alois Sontacchi","raw_affiliation_strings":["Institute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, Austria"],"raw_orcid":"https://orcid.org/0009-0008-9205-209X","affiliations":[{"raw_affiliation_string":"Institute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, Austria","institution_ids":["https://openalex.org/I317320687"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114312920"],"corresponding_institution_ids":["https://openalex.org/I317320687"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.4635,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64373971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"12","issue":null,"first_page":"159239","last_page":"159251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9940999746322632,"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"}},"topics":[{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9940999746322632,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9610000252723694,"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":0.9179999828338623,"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/spectrogram","display_name":"Spectrogram","score":0.8696274757385254},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6620739698410034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5727129578590393},{"id":"https://openalex.org/keywords/harmonic-vector-excitation-coding","display_name":"Harmonic Vector Excitation Coding","score":0.4877220094203949},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4844486713409424},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4528537392616272},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4374179244041443},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.42477360367774963},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4075353443622589},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4069206714630127},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19942203164100647},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09044539928436279}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8696274757385254},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6620739698410034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5727129578590393},{"id":"https://openalex.org/C80167644","wikidata":"https://www.wikidata.org/wiki/Q463990","display_name":"Harmonic Vector Excitation Coding","level":3,"score":0.4877220094203949},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4844486713409424},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4528537392616272},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4374179244041443},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.42477360367774963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4075353443622589},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4069206714630127},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19942203164100647},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09044539928436279},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3482359","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3482359","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a9b7df0310d949c38998c15c034ce01a","is_oa":true,"landing_page_url":"https://doaj.org/article/a9b7df0310d949c38998c15c034ce01a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 159239-159251 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3482359","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3482359","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1963884863","https://openalex.org/W2055815603","https://openalex.org/W2064675550","https://openalex.org/W2109189270","https://openalex.org/W2151626637","https://openalex.org/W2168013545","https://openalex.org/W2747070883","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2791686384","https://openalex.org/W2948978827","https://openalex.org/W2963091184","https://openalex.org/W3037038648","https://openalex.org/W3140429000","https://openalex.org/W3163662330","https://openalex.org/W3196475561","https://openalex.org/W3198785558","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W3217536461","https://openalex.org/W4225905067","https://openalex.org/W4252337780","https://openalex.org/W4284972581","https://openalex.org/W4307323391","https://openalex.org/W4372270198","https://openalex.org/W6617744952","https://openalex.org/W6621543089","https://openalex.org/W6630442970","https://openalex.org/W6640212811","https://openalex.org/W6690026940","https://openalex.org/W6748409065","https://openalex.org/W6757817989","https://openalex.org/W6762931180","https://openalex.org/W6767111847","https://openalex.org/W6779577414","https://openalex.org/W6779792965","https://openalex.org/W6783867762","https://openalex.org/W6838843145"],"related_works":["https://openalex.org/W1928998787","https://openalex.org/W2383072803","https://openalex.org/W1570840316","https://openalex.org/W2155796184","https://openalex.org/W2021359362","https://openalex.org/W1000239413","https://openalex.org/W2350749055","https://openalex.org/W2509918616","https://openalex.org/W2095808012","https://openalex.org/W1754793637"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,11,21,34,55,79,146],"method":[4,61,88,109,122],"for":[5,17,25],"real-time":[6],"speech":[7,118],"coding":[8,19,140],"that":[9,138],"combines":[10],"binary-latent-vector":[12],"variational":[13],"recurrent":[14,139],"neural":[15],"network":[16],"mel-spectrogram":[18],"with":[20,141],"non-autoregressive":[22],"convolutional":[23],"vocoder":[24],"waveform":[26],"reconstruction.":[27],"To":[28],"enable":[29],"bitrate":[30],"scalability,":[31],"we":[32],"propose":[33],"latent":[35,143],"vector":[36,57,151],"truncation":[37],"and":[38,45,70,75,95],"padding":[39],"technique.":[40],"We":[41],"evaluate":[42],"both":[43],"fixed-":[44],"scalable-bitrate":[46],"variants":[47],"of":[48],"the":[49,86,107,116,120,132],"proposed":[50,87,108,121],"method,":[51],"comparing":[52],"them":[53],"to":[54,149],"baseline":[56],"quantization-based":[58,152],"coder.":[59],"The":[60,135],"is":[62,145],"also":[63],"benchmarked":[64],"against":[65],"Opus,":[66],"Lyra":[67,91],"v2,":[68],"EnCodec,":[69],"AudioDec":[71,104],"using":[72],"objective":[73],"metrics":[74],"subjective":[76],"ratings":[77],"from":[78,115,131],"MUSHRA":[80],"listening":[81],"test.":[82],"At":[83],"1.38":[84],"kbps,":[85],"significantly":[89,105],"outperforms":[90],"v2":[92],"at":[93,96,101,110],"3kbps":[94],"5.51kbps":[97],"matches":[98],"its":[99],"performance":[100],"6kbps.":[102],"Although":[103],"surpasses":[106],"6.4kbps":[111],"on":[112,128],"test":[113],"data":[114],"TSP":[117],"dataset,":[119],"shows":[123],"competitive":[124],"or":[125],"superior":[126],"results":[127,136],"withheld":[129],"speakers":[130],"VCTK":[133],"dataset.":[134],"show":[137],"binary":[142],"vectors":[144],"viable":[147],"alternative":[148],"prevailing":[150],"approaches.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
