{"id":"https://openalex.org/W4416251233","doi":"https://doi.org/10.1109/waspaa66052.2025.11230928","title":"RADE: A Neural Codec for Transmitting Speech over HF Radio Channels","display_name":"RADE: A Neural Codec for Transmitting Speech over HF Radio Channels","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416251233","doi":"https://doi.org/10.1109/waspaa66052.2025.11230928"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5012408373","display_name":"David Rowe","orcid":"https://orcid.org/0000-0001-5899-2653"},"institutions":[{"id":"https://openalex.org/I4210110242","display_name":"Digital Science (United States)","ror":"https://ror.org/020h4b682","country_code":"US","type":"company","lineage":["https://openalex.org/I4210110242","https://openalex.org/I4210112888","https://openalex.org/I4210118830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Rowe","raw_affiliation_strings":["Amateur Radio Digital Communications"],"affiliations":[{"raw_affiliation_string":"Amateur Radio Digital Communications","institution_ids":["https://openalex.org/I4210110242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["Xiph.Org Foundation"],"affiliations":[{"raw_affiliation_string":"Xiph.Org Foundation","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012408373"],"corresponding_institution_ids":["https://openalex.org/I4210110242"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3742276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.20960000157356262,"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":0.20960000157356262,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.12349999696016312,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.09950000047683716,"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/encoder","display_name":"Encoder","score":0.5072000026702881},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.47589999437332153},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4066999852657318},{"id":"https://openalex.org/keywords/amplitude-modulation","display_name":"Amplitude modulation","score":0.4058000147342682},{"id":"https://openalex.org/keywords/multipath-propagation","display_name":"Multipath propagation","score":0.40560001134872437},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.3578999936580658},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.35679998993873596},{"id":"https://openalex.org/keywords/orthogonal-frequency-division-multiplexing","display_name":"Orthogonal frequency-division multiplexing","score":0.34610000252723694},{"id":"https://openalex.org/keywords/quadrature-amplitude-modulation","display_name":"Quadrature amplitude modulation","score":0.3393000066280365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110999822616577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5292999744415283},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.47589999437332153},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.4058000147342682},{"id":"https://openalex.org/C161218011","wikidata":"https://www.wikidata.org/wiki/Q11827794","display_name":"Multipath propagation","level":3,"score":0.40560001134872437},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.38989999890327454},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.35679998993873596},{"id":"https://openalex.org/C40409654","wikidata":"https://www.wikidata.org/wiki/Q375889","display_name":"Orthogonal frequency-division multiplexing","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C32409245","wikidata":"https://www.wikidata.org/wiki/Q749753","display_name":"Quadrature amplitude modulation","level":4,"score":0.3393000066280365},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.328000009059906},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C92545706","wikidata":"https://www.wikidata.org/wiki/Q902174","display_name":"Radio spectrum","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C2781307350","wikidata":"https://www.wikidata.org/wiki/Q6887221","display_name":"Mobile radio","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C169334058","wikidata":"https://www.wikidata.org/wiki/Q353292","display_name":"Additive white Gaussian noise","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C59030546","wikidata":"https://www.wikidata.org/wiki/Q7265371","display_name":"QAM","level":5,"score":0.2851000130176544},{"id":"https://openalex.org/C507880516","wikidata":"https://www.wikidata.org/wiki/Q1257510","display_name":"Digital radio","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2524000108242035},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2079550333","https://openalex.org/W2127848638","https://openalex.org/W2734408173","https://openalex.org/W2736068844","https://openalex.org/W2963091184","https://openalex.org/W2963446712","https://openalex.org/W2964198392","https://openalex.org/W3128928743","https://openalex.org/W3182970290","https://openalex.org/W3201394241","https://openalex.org/W3215615641","https://openalex.org/W4401452051","https://openalex.org/W4403511255","https://openalex.org/W4406089864"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"compression":[1],"is":[2,28],"commonly":[3],"used":[4],"to":[5,89,107,118,121],"send":[6,90],"voice":[7],"over":[8,95,167],"radio":[9,36,99,150,165],"channels":[10,151],"in":[11],"applications":[12],"such":[13],"as":[14],"mobile":[15],"telephony":[16],"and":[17,35,70,91,125,146,163],"two-way":[18],"push-to-talk":[19],"(PTT)":[20],"radio.":[21],"In":[22,38],"classical":[23],"systems,":[24],"the":[25,49],"speech":[26,156],"codec":[27],"combined":[29],"with":[30,54],"forward":[31],"error":[32],"correction,":[33],"modulation":[34,79],"hardware.":[37],"this":[39],"paper":[40],"we":[41,152],"describe":[42],"an":[43],"autoencoder":[44,114],"that":[45,158],"replaces":[46],"many":[47],"of":[48,139,170],"traditional":[50],"signal":[51],"processing":[52],"elements":[53],"a":[55,61,132,168],"neural":[56],"network.":[57],"The":[58,101,113],"encoder":[59],"takes":[60],"vocoder":[62,108],"feature":[63],"set":[64],"(short":[65],"term":[66],"spectrum,":[67],"pitch,":[68],"voicing),":[69],"produces":[71],"discrete":[72],"time,":[73],"but":[74],"continuously":[75],"valued":[76],"quadrature":[77],"amplitude":[78],"(QAM)":[80],"symbols.":[81],"We":[82],"use":[83],"orthogonal":[84],"frequency":[85,97],"domain":[86],"multiplexing":[87],"(OFDM)":[88],"receive":[92],"these":[93],"symbols":[94,106],"high":[96],"(HF)":[98],"channels.":[100],"decoder":[102],"converts":[103],"received":[104],"QAM":[105],"features":[109],"suitable":[110],"for":[111],"synthesis.":[112],"has":[115],"been":[116],"trained":[117],"be":[119],"robust":[120],"additive":[122],"Gaussian":[123],"noise":[124],"multipath":[126],"channel":[127],"impairments":[128],"while":[129],"simultaneously":[130],"maintaining":[131],"Peak":[133],"To":[134],"Average":[135],"Power":[136],"Ratio":[137],"(PAPR)":[138],"less":[140],"than":[141],"1":[142],"dB.":[143],"Over":[144],"simulated":[145],"real":[147],"world":[148],"HF":[149],"have":[153],"achieved":[154],"output":[155],"intelligibility":[157],"clearly":[159],"surpasses":[160],"existing":[161],"analog":[162],"digital":[164],"systems":[166],"range":[169],"SNRs.":[171]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}