{"id":"https://openalex.org/W4284972581","doi":"https://doi.org/10.21437/interspeech.2022-430","title":"NESC: Robust Neural End-2-End Speech Coding with GANs","display_name":"NESC: Robust Neural End-2-End Speech Coding with GANs","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4284972581","doi":"https://doi.org/10.21437/interspeech.2022-430"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-430","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-430","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5039716073","display_name":"Nicola Pia","orcid":"https://orcid.org/0000-0003-0987-863X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nicola Pia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102051987","display_name":"Kishan Chand Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kishan Gupta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077147264","display_name":"Srikanth Korse","orcid":"https://orcid.org/0009-0008-7564-9628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srikanth Korse","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009684245","display_name":"Markus Multrus","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markus Multrus","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054985419","display_name":"Guillaume Fuchs","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillaume Fuchs","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039716073"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4604,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83979862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4212","last_page":"4216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9983000159263611,"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/T10320","display_name":"Neural Networks and Applications","score":0.9914000034332275,"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":0.7407894134521484},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7229432463645935},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6212467551231384},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.5958226323127747},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5909574031829834},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.552038848400116},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5458441972732544},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5185976028442383},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5155544281005859},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5058590769767761},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.4504736363887787},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4490434229373932},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3472030758857727},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.2898476719856262},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28940796852111816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24377813935279846},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.15016961097717285},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.10124465823173523},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.050890177488327026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407894134521484},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7229432463645935},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6212467551231384},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.5958226323127747},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5909574031829834},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.552038848400116},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5458441972732544},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5185976028442383},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5155544281005859},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5058590769767761},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.4504736363887787},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4490434229373932},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3472030758857727},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.2898476719856262},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28940796852111816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24377813935279846},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.15016961097717285},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.10124465823173523},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.050890177488327026},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-430","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-430","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:null:publica/445587","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/445587","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2374470469","https://openalex.org/W2121846146","https://openalex.org/W137020845","https://openalex.org/W1574090191","https://openalex.org/W2042028224","https://openalex.org/W1542588102","https://openalex.org/W1578591928","https://openalex.org/W2106874932","https://openalex.org/W2108179702","https://openalex.org/W2496295964"],"abstract_inverted_index":{"Neural":[0,43],"networks":[1],"have":[2],"proven":[3],"to":[4,9,104],"be":[5,30],"a":[6,25,37,48,66],"formidable":[7],"tool":[8],"tackle":[10],"the":[11,22,79],"problem":[12],"of":[13,24],"speech":[14,53,58,97],"coding":[15,59],"at":[16,60],"very":[17],"low":[18],"bit":[19],"rates.":[20],"However,":[21],"design":[23],"neural":[26,52],"coder":[27],"that":[28,99],"can":[29],"operated":[31],"robustly":[32],"under":[33],"real-world":[34],"conditions":[35,106],"remains":[36],"major":[38],"challenge.":[39],"Therefore,":[40],"we":[41],"present":[42],"End-2-End":[44],"Speech":[45],"Codec":[46],"(NESC)":[47],"robust,":[49],"scalable":[50],"end-to-end":[51],"codec":[54],"for":[55],"high-quality":[56],"wideband":[57],"3":[61],"kbps.":[62],"The":[63],"encoder":[64],"uses":[65],"new":[67],"architecture":[68,81],"configuration,":[69],"which":[70],"relies":[71],"on":[72,84,93],"our":[73,85],"proposed":[74],"Dual-PathConvRNN":[75],"(DPCRNN)":[76],"layer,":[77],"while":[78],"decoder":[80],"is":[82,101],"based":[83],"previous":[86],"work":[87],"Streamwise-StyleMelGAN.":[88],"Our":[89],"subjective":[90],"listening":[91],"tests":[92],"clean":[94],"and":[95,107],"noisy":[96],"show":[98],"NESC":[100],"particularly":[102],"robust":[103],"unseen":[105],"signal":[108],"perturbations.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}