{"id":"https://openalex.org/W4415433949","doi":"https://doi.org/10.21437/interspeech.2025-546","title":"SpecTokenizer: A Lightweight Streaming Codec in the Compressed Spectrum Domain","display_name":"SpecTokenizer: A Lightweight Streaming Codec in the Compressed Spectrum Domain","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433949","doi":"https://doi.org/10.21437/interspeech.2025-546"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.21209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120093963","display_name":"Zixiang Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zixiang Wan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093964","display_name":"Guochang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guochang Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762375","display_name":"Yifeng He","orcid":"https://orcid.org/0000-0003-2345-0736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifeng He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067500170","display_name":"Jianqiang Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianqiang Wei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120093963"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31633804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"599","last_page":"603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9649999737739563,"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":0.9649999737739563,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9319999814033508,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/codec","display_name":"Codec","score":0.9398000240325928},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.8371999859809875},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5961999893188477},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5817000269889832},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.428600013256073},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4235999882221222},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4065999984741211},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.36340001225471497}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.9398000240325928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8464999794960022},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.8371999859809875},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5817000269889832},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4278999865055084},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.42289999127388},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.37130001187324524},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36340001225471497},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.3488999903202057},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3125},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C125864890","wikidata":"https://www.wikidata.org/wiki/Q1262687","display_name":"Intra-frame","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.21209","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.21209","pdf_url":"https://arxiv.org/pdf/2510.21209","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.21209","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.21209","pdf_url":"https://arxiv.org/pdf/2510.21209","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Neural":[0],"Audio":[1],"Codecs":[2],"(NACs)":[3],"have":[4],"gained":[5],"growing":[6],"attention":[7],"in":[8,19,52,76],"recent":[9],"years":[10],"as":[11],"technologies":[12],"for":[13],"audio":[14,17],"compression":[15],"and":[16,30,37,62,69,107,122],"representation":[18],"speech":[20],"language":[21],"models.":[22],"While":[23],"mainstream":[24],"NACs":[25,39],"typically":[26],"require":[27],"G-level":[28],"computation":[29,106],"M-level":[31],"parameters,":[32],"the":[33,53,77,84,94,105,110,116],"performance":[34,91],"of":[35,59,104,109],"lightweight":[36,47,98],"streaming":[38,48],"remains":[40],"underexplored.":[41],"This":[42],"paper":[43],"proposes":[44],"SpecTokenizer,":[45],"a":[46],"codec":[49,95,117],"that":[50],"operates":[51],"compressed":[54,78],"spectral":[55],"domain.":[56,80],"Composed":[57],"solely":[58],"alternating":[60],"CNN":[61],"RNN":[63],"layers,":[64],"SpecTokenizer":[65,86],"achieves":[66,87],"greater":[67],"efficiency":[68],"better":[70],"representational":[71],"capability":[72],"through":[73],"multi-scale":[74],"modeling":[75],"spectrum":[79],"At":[81],"4":[82],"kbps,":[83],"proposed":[85],"comparable":[88],"or":[89],"superior":[90],"compared":[92],"to":[93],"with":[96],"state-of-the-art":[97],"architecture":[99],"while":[100],"requiring":[101],"only":[102],"20%":[103],"10%":[108],"parameters.":[111],"Furthermore,":[112],"it":[113],"significantly":[114],"outperforms":[115],"when":[118],"using":[119],"similar":[120],"computational":[121],"storage":[123],"resources.":[124]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}