{"id":"https://openalex.org/W7163638555","doi":"https://doi.org/10.48550/arxiv.2606.06357","title":"F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation","display_name":"F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163638555","doi":"https://doi.org/10.48550/arxiv.2606.06357"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.06357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06357","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.06357","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002904368","display_name":"Dinghao Zhou","orcid":"https://orcid.org/0009-0000-8519-4630"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Dinghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074833963","display_name":"Xingchen Song","orcid":"https://orcid.org/0009-0009-9516-5361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Xingchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138016490","display_name":"Di Wu (23906)","orcid":"https://orcid.org/0000-0002-5895-2237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Di","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137981254","display_name":"Pengyu Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Pengyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594429","display_name":"Shengfan Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Shengfan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130392220","display_name":"Sixiang Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Sixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3050999939441681,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3050999939441681,"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":0.2402999997138977,"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":0.22190000116825104,"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":0.9646999835968018},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7117000222206116},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5497999787330627},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4984000027179718},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49129998683929443},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4291999936103821}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9646999835968018},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7117000222206116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7038000226020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5996999740600586},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4984000027179718},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47429999709129333},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.06357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06357","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.06357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06357","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Continuous":[0],"audio":[1,17,31],"autoencoders":[2],"reconstruct":[3],"waveforms":[4],"well":[5],"but":[6,21],"often":[7],"produce":[8],"latents":[9,44,76,90,108],"with":[10,48,91],"weak":[11],"structure":[12],"for":[13,77,102],"understanding,":[14],"while":[15,104],"self-supervised":[16],"encoders":[18],"capture":[19],"semantics":[20],"are":[22],"not":[23],"directly":[24],"decodable.":[25],"This":[26],"mismatch":[27],"complicates":[28],"a":[29,51,56],"single":[30],"tokenizer":[32,98],"that":[33],"must":[34],"support":[35],"both":[36],"understanding":[37,103],"and":[38,55,65,79,93],"generation.":[39,81],"We":[40],"adapt":[41],"continuous":[42,75,107],"autoencoder":[43,53,89],"to":[45],"this":[46],"setting":[47],"two":[49],"components:":[50],"noise-regularized":[52],"bottleneck":[54,61],"latent-side":[57],"representation":[58,83],"encoder.":[59],"The":[60,82,96],"uses":[62],"channel":[63],"normalization":[64],"stochastic":[66],"perturbation":[67],"instead":[68],"of":[69],"KL-based":[70],"variational":[71],"training,":[72],"yielding":[73],"scale-controlled":[74],"reconstruction":[78],"autoregressive":[80],"encoder":[84],"is":[85],"trained":[86],"on":[87],"frozen":[88],"RQ-MTP":[92],"frozen-LLM":[94],"supervision.":[95],"resulting":[97],"provides":[99],"high-dimensional":[100],"representations":[101],"preserving":[105],"normalized":[106],"as":[109],"generation":[110],"targets":[111]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-06T00:00:00"}