{"id":"https://openalex.org/W4200219715","doi":"https://doi.org/10.1145/3461615.3491114","title":"TeNC: Low Bit-Rate Speech Coding with VQ-VAE and GAN","display_name":"TeNC: Low Bit-Rate Speech Coding with VQ-VAE and GAN","publication_year":2021,"publication_date":"2021-10-18","ids":{"openalex":"https://openalex.org/W4200219715","doi":"https://doi.org/10.1145/3461615.3491114"},"language":"en","primary_location":{"id":"doi:10.1145/3461615.3491114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3491114","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","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/A5101982764","display_name":"Yi Chen","orcid":"https://orcid.org/0009-0006-4935-3546"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chen","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yang","raw_affiliation_strings":["Tencent AI LAB, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI LAB, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685461","display_name":"Na Hu","orcid":"https://orcid.org/0000-0001-6362-0969"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Hu","raw_affiliation_strings":["Tencent AI LAB, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI LAB, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI LAB, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI LAB, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7721,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.72363928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9990000128746033,"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":0.9988999962806702,"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/speech-coding","display_name":"Speech coding","score":0.8147579431533813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7756577730178833},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.7611000537872314},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.6960796117782593},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.687091588973999},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6828164458274841},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5888090133666992},{"id":"https://openalex.org/keywords/full-rate","display_name":"Full Rate","score":0.4500935971736908},{"id":"https://openalex.org/keywords/bit-rate","display_name":"Bit rate","score":0.44886717200279236},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.43346500396728516},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4319063723087311},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4205131530761719},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.3558887839317322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31076711416244507},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2413833737373352},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.14292100071907043},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11876943707466125},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1035526692867279}],"concepts":[{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.8147579431533813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756577730178833},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7611000537872314},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.6960796117782593},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.687091588973999},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6828164458274841},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5888090133666992},{"id":"https://openalex.org/C197477341","wikidata":"https://www.wikidata.org/wiki/Q2532845","display_name":"Full Rate","level":3,"score":0.4500935971736908},{"id":"https://openalex.org/C2987812609","wikidata":"https://www.wikidata.org/wiki/Q194158","display_name":"Bit rate","level":2,"score":0.44886717200279236},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.43346500396728516},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4319063723087311},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4205131530761719},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.3558887839317322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31076711416244507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2413833737373352},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.14292100071907043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11876943707466125},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1035526692867279},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461615.3491114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3491114","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W2020883660","https://openalex.org/W2108532241","https://openalex.org/W2151409182","https://openalex.org/W2593414223","https://openalex.org/W2775336875","https://openalex.org/W2935711438","https://openalex.org/W2963091184","https://openalex.org/W2963208781","https://openalex.org/W2972519044","https://openalex.org/W3015338123","https://openalex.org/W3016003977","https://openalex.org/W3096468295","https://openalex.org/W3144035034","https://openalex.org/W3160576174","https://openalex.org/W3199364993"],"related_works":["https://openalex.org/W1601770773","https://openalex.org/W2060409740","https://openalex.org/W2110059311","https://openalex.org/W2159307410","https://openalex.org/W2163834050","https://openalex.org/W137020845","https://openalex.org/W2020464095","https://openalex.org/W1542588102","https://openalex.org/W1898356410","https://openalex.org/W2121846146"],"abstract_inverted_index":{"Speech":[0],"coding":[1,81],"aims":[2],"at":[3,69,127],"compressing":[4],"digital":[5],"speech":[6,20,37,66,80,133],"signals":[7],"with":[8,38,52,67],"fewer":[9],"bits":[10],"and":[11,57,92,118,135],"reconstructing":[12],"it":[13],"back":[14],"to":[15,34,100],"raw":[16],"signals,":[17],"maintaining":[18],"the":[19,58,90,103,109,112,124],"quality":[21,134],"as":[22,24],"much":[23],"possible.":[25],"But":[26],"conventional":[27,125],"codecs":[28,126],"usually":[29],"need":[30],"a":[31,53,70,86,93],"high":[32,40],"bit-rate":[33,72,129],"achieve":[35],"reconstructed":[36,65,104],"reasonable":[39],"quality.":[41,105],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"an":[47],"end-to-end":[48],"neural":[49],"generative":[50,59],"codec":[51],"VQ-VAE":[54],"based":[55],"auto-encoder":[56],"adversarial":[60],"network":[61],"(GAN),":[62],"which":[63,121],"achieves":[64],"high-fidelity":[68],"low":[71,128],"about":[73],"2":[74],"kb/s.":[75],"The":[76],"compression":[77],"process":[78],"of":[79,89,111,132],"is":[82,98],"carried":[83],"out":[84],"by":[85],"down-sampling":[87],"module":[88],"encoder":[91],"learnable":[94],"discrete":[95],"codebook.":[96],"GAN":[97],"used":[99],"further":[101],"improve":[102],"Our":[106],"experiments":[107],"confirm":[108],"effectiveness":[110],"proposed":[113],"model":[114],"in":[115,130],"both":[116],"objective":[117],"subjective":[119],"tests,":[120],"significantly":[122],"outperforms":[123],"terms":[131],"speaker":[136],"similarity.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}