{"id":"https://openalex.org/W7148477801","doi":"https://doi.org/10.1109/asru65441.2025.11434720","title":"PURE Codec: Progressive Unfolding of Residual Entropy for Speech Codec Learning","display_name":"PURE Codec: Progressive Unfolding of Residual Entropy for Speech Codec Learning","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148477801","doi":"https://doi.org/10.1109/asru65441.2025.11434720"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132828531","display_name":"Jiatong Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["CMU"],"affiliations":[{"raw_affiliation_string":"CMU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132813796","display_name":"Haoran Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["SJTU"],"affiliations":[{"raw_affiliation_string":"SJTU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132817161","display_name":"William Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Chen","raw_affiliation_strings":["CMU"],"affiliations":[{"raw_affiliation_string":"CMU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132829294","display_name":"Chenda Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenda Li","raw_affiliation_strings":["SJTU"],"affiliations":[{"raw_affiliation_string":"SJTU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132812607","display_name":"Wangyou Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["SJTU"],"affiliations":[{"raw_affiliation_string":"SJTU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132817459","display_name":"Jinchuan Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinchuan Tian","raw_affiliation_strings":["CMU"],"affiliations":[{"raw_affiliation_string":"CMU","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132825101","display_name":"Shinji Watanabe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["CMU"],"affiliations":[{"raw_affiliation_string":"CMU","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5132828531"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87570171,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6141999959945679,"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":0.6141999959945679,"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":0.07150000333786011,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06610000133514404,"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/residual","display_name":"Residual","score":0.4788999855518341},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47839999198913574},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.36489999294281006},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31439998745918274},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.29109999537467957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6019999980926514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5461000204086304},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4627000093460083},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4449999928474426},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2872999906539917},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1728888090","https://openalex.org/W1970491336","https://openalex.org/W2024490156","https://openalex.org/W2120376959","https://openalex.org/W2128301448","https://openalex.org/W2165291881","https://openalex.org/W2593116425","https://openalex.org/W2972359262","https://openalex.org/W2972541922","https://openalex.org/W3160427568","https://openalex.org/W3186609711","https://openalex.org/W3215615641","https://openalex.org/W4225302959","https://openalex.org/W4225956675","https://openalex.org/W4372259964","https://openalex.org/W4372270198","https://openalex.org/W4385756463","https://openalex.org/W4392903389","https://openalex.org/W4392908343","https://openalex.org/W4392931975","https://openalex.org/W4399875170","https://openalex.org/W4402111462","https://openalex.org/W4402111799","https://openalex.org/W4402112079","https://openalex.org/W4402112381","https://openalex.org/W4402670057","https://openalex.org/W4402915905","https://openalex.org/W4404782459","https://openalex.org/W4406461437","https://openalex.org/W4408352440","https://openalex.org/W4411119544","https://openalex.org/W4411119792","https://openalex.org/W4412945298","https://openalex.org/W4415433412","https://openalex.org/W4415433503","https://openalex.org/W4417305271","https://openalex.org/W7133219565"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"speech":[1,47,57,85],"codecs":[2,80],"have":[3],"achieved":[4],"strong":[5],"performance":[6],"in":[7,81],"low-bitrate":[8],"compression,":[9],"but":[10],"residual":[11,63],"vector":[12],"quantization":[13,43,52],"(RVQ)":[14],"often":[15],"suffers":[16],"from":[17],"unstable":[18],"training":[19,69,92],"and":[20,26,83],"ineffective":[21],"decomposition,":[22],"limiting":[23],"reconstruction":[24,82],"quality":[25],"efficiency.":[27],"We":[28],"propose":[29],"PURE":[30,75],"Codec":[31],"(Progressive":[32],"Unfolding":[33],"of":[34],"Residual":[35],"Entropy),":[36],"a":[37,45],"novel":[38],"framework":[39],"that":[40,74],"guides":[41],"multi-stage":[42],"using":[44],"pre-trained":[46],"enhancement":[48],"model.":[49],"The":[50],"first":[51],"stage":[53],"reconstructs":[54],"low-entropy,":[55],"denoised":[56],"embeddings,":[58],"while":[59],"subsequent":[60],"stages":[61],"encode":[62],"high-entropy":[64],"components.":[65],"This":[66],"design":[67],"improves":[68],"stability":[70],"significantly.":[71],"Experiments":[72],"demonstrate":[73],"consistently":[76],"outperforms":[77],"conventional":[78],"RVQ-based":[79],"downstream":[84],"language":[86],"model-based":[87],"text-to-speech,":[88],"particularly":[89],"under":[90],"noisy":[91],"conditions.":[93]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}