{"id":"https://openalex.org/W7214940908","doi":"https://doi.org/10.48550/arxiv.2609.36951","title":"Interpreting and Evaluating Dynamic-Rate Speech Codec Boundaries","display_name":"Interpreting and Evaluating Dynamic-Rate Speech Codec Boundaries","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214940908","doi":"https://doi.org/10.48550/arxiv.2609.36951"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.36951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36951","pdf_url":"https://arxiv.org/pdf/2609.36951","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.36951","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153680622","display_name":"Han Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Han","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153681122","display_name":"Jiaqi Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Jiaqi","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108320174","display_name":"Yingda Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen, Yingda","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153612408","display_name":"Yuxiang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yuxiang","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153596894","display_name":"Zhizheng Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Zhizheng","raw_affiliation_strings":["Amphion Technology Co. , Ltd","The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amphion Technology Co. , Ltd","institution_ids":[]},{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922000169754028,"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":0.9922000169754028,"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":0.007499999832361937,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/neural-speech-codec","display_name":"neural speech codec","score":0.5180000066757202},{"id":"https://openalex.org/keywords/speech-reconstruction","display_name":"speech reconstruction","score":0.6460000276565552},{"id":"https://openalex.org/keywords/whisper","display_name":"Whisper","score":0.9380000233650208},{"id":"https://openalex.org/keywords/phonetic-boundaries","display_name":"phonetic boundaries","score":0.4410000145435333},{"id":"https://openalex.org/keywords/syllable-boundaries","display_name":"syllable boundaries","score":0.7889999747276306},{"id":"https://openalex.org/keywords/semantic-tokens","display_name":"semantic tokens","score":0.4950000047683716},{"id":"https://openalex.org/keywords/speech-representation","display_name":"speech representation","score":0.42800000309944153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081000208854675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6028000116348267},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37599998712539673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3750999867916107},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.28790000081062317},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.36951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36951","pdf_url":"https://arxiv.org/pdf/2609.36951","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.36951","doi":"https://doi.org/10.48550/arxiv.2609.36951","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.36951","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.36951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36951","pdf_url":"https://arxiv.org/pdf/2609.36951","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214940908.pdf","grobid_xml":"https://content.openalex.org/works/W7214940908.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7213407453","https://openalex.org/W7127195585","https://openalex.org/W4415182342","https://openalex.org/W7166676062","https://openalex.org/W7084408266","https://openalex.org/W4415433281","https://openalex.org/W7223211516","https://openalex.org/W4416965928","https://openalex.org/W7202216233","https://openalex.org/W7160282565"],"abstract_inverted_index":{"Dynamic-frame-rate":[0],"neural":[1,36],"speech":[2,37,66,150],"codecs":[3],"replace":[4],"a":[5,93,100,126,136],"uniform":[6,101],"frame":[7],"grid":[8],"with":[9,52,109],"variable-duration":[10],"tokens,":[11],"making":[12],"boundary":[13,42,60,120],"placement":[14],"part":[15],"of":[16,95],"the":[17,64,69,123,163],"representation":[18],"itself.":[19],"Yet":[20],"it":[21],"is":[22,107],"unclear":[23],"what":[24],"these":[25],"boundaries":[26,31,51,154],"encode":[27],"and":[28,44,54,72,80,89,99,113,133],"whether":[29],"interpretable":[30],"are":[32,155],"also":[33],"useful":[34,152],"for":[35,147],"reconstruction.":[38],"This":[39],"work":[40],"combines":[41],"interpretation":[43],"controlled":[45],"reconstruction":[46,115],"analysis":[47],"by":[48],"comparing":[49],"predicted":[50],"linguistic":[53,105],"acoustic":[55,81],"references.":[56],"We":[57,144],"find":[58],"that":[59,146],"meaning":[61],"depends":[62],"on":[63],"underlying":[65],"representation.":[67],"For":[68],"ASR-oriented":[70],"SenseVoice":[71],"Whisper":[73],"encoders,":[74],"shallow":[75],"layers":[76,85],"emphasize":[77],"phonetic,":[78],"voicing,":[79],"transitions,":[82],"whereas":[83],"deeper":[84],"shift":[86],"toward":[87],"syllable":[88,164],"subword":[90],"structure.":[91],"In":[92],"comparison":[94],"six":[96],"dynamic-frame-rate":[97],"algorithms":[98],"(fixed-frame-rate)":[102],"baseline,":[103],"higher-level":[104],"alignment":[106],"associated":[108],"lower":[110],"pooling":[111],"distortion":[112],"better":[114],"from":[116],"semantic":[117],"tokens.":[118],"Frame-rate-matched":[119],"tests":[121],"make":[122],"distinction":[124],"concrete:":[125],"syllable-derived":[127],"partition":[128,138],"improves":[129],"over":[130,142],"both":[131],"Uniform":[132],"Similarity,":[134],"while":[135],"phoneme-derived":[137],"does":[139],"not":[140],"improve":[141],"Uniform.":[143],"infer":[145],"semantically":[148],"rich":[149],"representations,":[151],"codec":[153],"best":[156],"understood":[157],"as":[158],"allocation":[159],"decisions":[160],"organized":[161],"around":[162],"scale.":[165]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-01T00:00:00"}