{"id":"https://openalex.org/W3015214864","doi":"https://doi.org/10.1109/icassp40776.2020.9054074","title":"Feedback Recurrent Autoencoder","display_name":"Feedback Recurrent Autoencoder","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015214864","doi":"https://doi.org/10.1109/icassp40776.2020.9054074","mag":"3015214864"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Qualcomm AI Research, Qualcomm Technologies, Inc"],"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010909962","display_name":"Guillaume Sauti\u00e8re","orcid":"https://orcid.org/0000-0002-8795-3335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillaume Sautiere","raw_affiliation_strings":["Qualcomm AI Research, Qualcomm Technologies, Netherlands B.V"],"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, Qualcomm Technologies, Netherlands B.V","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013330568","display_name":"Je-Hwan Ryu","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"J. Jon Ryu","raw_affiliation_strings":["Qualcomm AI Research, Qualcomm Technologies, Inc"],"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083922034","display_name":"Taco Cohen","orcid":"https://orcid.org/0000-0003-3072-3405"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taco S Cohen","raw_affiliation_strings":["Qualcomm AI Research, Qualcomm Technologies, Netherlands B.V"],"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, Qualcomm Technologies, Netherlands B.V","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100397616"],"corresponding_institution_ids":["https://openalex.org/I19268510"],"apc_list":null,"apc_paid":null,"fwci":1.4655,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84296229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3347","last_page":"3351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.9973999857902527,"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/autoencoder","display_name":"Autoencoder","score":0.9184404611587524},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423110008239746},{"id":"https://openalex.org/keywords/variable-bitrate","display_name":"Variable bitrate","score":0.6611259579658508},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.643144965171814},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6021534204483032},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5698138475418091},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5667291283607483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5095858573913574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.508468508720398},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.498030424118042},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4523516595363617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39311516284942627},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.29199522733688354},{"id":"https://openalex.org/keywords/bit-rate","display_name":"Bit rate","score":0.14960390329360962},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.1003434956073761}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9184404611587524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423110008239746},{"id":"https://openalex.org/C57667952","wikidata":"https://www.wikidata.org/wiki/Q1154443","display_name":"Variable bitrate","level":3,"score":0.6611259579658508},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.643144965171814},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6021534204483032},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5698138475418091},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5667291283607483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5095858573913574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.508468508720398},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.498030424118042},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4523516595363617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39311516284942627},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29199522733688354},{"id":"https://openalex.org/C2987812609","wikidata":"https://www.wikidata.org/wiki/Q194158","display_name":"Bit rate","level":2,"score":0.14960390329360962},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.1003434956073761},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.1109/icassp40776.2020.9054074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":34,"referenced_works":["https://openalex.org/W1933340426","https://openalex.org/W1959608418","https://openalex.org/W2120847449","https://openalex.org/W2130942839","https://openalex.org/W2343938449","https://openalex.org/W2519091744","https://openalex.org/W2752796333","https://openalex.org/W2808697642","https://openalex.org/W2927928207","https://openalex.org/W2935711438","https://openalex.org/W2949382160","https://openalex.org/W2952161038","https://openalex.org/W2962714411","https://openalex.org/W2962741254","https://openalex.org/W2962891349","https://openalex.org/W2963147844","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963403868","https://openalex.org/W2963799213","https://openalex.org/W2969260367","https://openalex.org/W2972519044","https://openalex.org/W2987947587","https://openalex.org/W2994610548","https://openalex.org/W3098284407","https://openalex.org/W4385245566","https://openalex.org/W6639118987","https://openalex.org/W6640284076","https://openalex.org/W6640963894","https://openalex.org/W6704734575","https://openalex.org/W6739901393","https://openalex.org/W6755592152","https://openalex.org/W6760514122","https://openalex.org/W6764882207"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2011227383","https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W1976719989","https://openalex.org/W2942893872"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,61,100],"propose":[4],"a":[5,42,68,78,88],"new":[6],"recurrent":[7,25],"autoencoder":[8],"architecture,":[9],"termed":[10],"Feedback":[11],"Recurrent":[12],"AutoEncoder":[13],"(FRAE),":[14],"for":[15,91],"online":[16],"compression":[17],"of":[18,27,46],"sequential":[19],"data":[20,48],"with":[21,67],"temporal":[22],"dependency.":[23],"The":[24],"structure":[26],"FRAE":[28],"is":[29],"designed":[30],"to":[31,49],"efficiently":[32],"extract":[33],"the":[34,37,47,64,92],"redundancy":[35],"along":[36],"time":[38],"dimension":[39],"and":[40,95],"allows":[41],"compact":[43],"discrete":[44],"representation":[45],"be":[50],"learned.":[51],"We":[52,82],"demonstrate":[53],"its":[54],"effectiveness":[55],"in":[56],"speech":[57,75],"spectrogram":[58],"compression.":[59],"Specifically,":[60],"show":[62,84],"that":[63,85],"FRAE,":[65],"paired":[66],"powerful":[69],"neural":[70],"vocoder,":[71],"can":[72,101],"produce":[73],"high-quality":[74],"waveforms":[76],"at":[77],"low,":[79],"fixed":[80],"bitrate.":[81,107],"further":[83],"by":[86],"adding":[87],"learned":[89],"prior":[90],"latent":[93],"space":[94],"using":[96],"an":[97,103],"entropy":[98],"coder,":[99],"achieve":[102],"even":[104],"lower":[105],"variable":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}