{"id":"https://openalex.org/W4416250997","doi":"https://doi.org/10.1109/waspaa66052.2025.11230960","title":"Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine","display_name":"Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250997","doi":"https://doi.org/10.1109/waspaa66052.2025.11230960"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5055422970","display_name":"Anastasia Kuznetsova","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anastasia Kuznetsova","raw_affiliation_strings":["Indiana University,Bloomington,IN,USA"],"affiliations":[{"raw_affiliation_string":"Indiana University,Bloomington,IN,USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059001612","display_name":"Inseon Jang","orcid":"https://orcid.org/0000-0003-2237-2668"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inseon Jang","raw_affiliation_strings":["Electronics and Telecommunications Research Institute,Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Daejeon,Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026162456","display_name":"Wootaek L\u0131m","orcid":"https://orcid.org/0000-0002-5523-6294"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wootaek Lim","raw_affiliation_strings":["Electronics and Telecommunications Research Institute,Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Daejeon,Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Champaign,IL,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Champaign,IL,USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055422970"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":2.6124,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9256652,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.4099999964237213,"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":0.4099999964237213,"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":0.2865000069141388,"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/T11309","display_name":"Music and Audio Processing","score":0.0754999965429306,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.616100013256073},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5690000057220459},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5353000164031982},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5199000239372253},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.42750000953674316},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4113999903202057},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3544999957084656},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.350600004196167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3447999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001000285148621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6710000038146973},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.616100013256073},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4690000116825104},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2987812609","wikidata":"https://www.wikidata.org/wiki/Q194158","display_name":"Bit rate","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":16,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2038484192","https://openalex.org/W2127141656","https://openalex.org/W2128301448","https://openalex.org/W2632564668","https://openalex.org/W2963250244","https://openalex.org/W3010925296","https://openalex.org/W3024869864","https://openalex.org/W3110277971","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4402115964","https://openalex.org/W4402670057","https://openalex.org/W4406461437","https://openalex.org/W4412945298"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"audio":[1,20,108],"codecs,":[2],"leveraging":[3],"quantization":[4,68],"algorithms,":[5],"have":[6],"significantly":[7],"impacted":[8],"various":[9,94],"speech/audio":[10,56],"tasks.":[11],"While":[12],"high-fidelity":[13],"reconstruction":[14],"is":[15,91],"paramount":[16],"for":[17,22,99,117],"human":[18],"perception,":[19],"coding":[21],"machines":[23],"(ACoM)":[24],"prioritizes":[25],"efficient":[26,39],"compression":[27],"and":[28,45,96,107,115,120],"downstream":[29,57,85],"task":[30,119],"performance,":[31],"disregarding":[32],"perceptual":[33],"nuances.":[34],"This":[35],"work":[36],"introduces":[37],"an":[38,53],"ACoM":[40],"method":[41,111],"that":[42],"can":[43],"compress":[44],"quantize":[46],"any":[47],"chosen":[48],"intermediate":[49],"feature":[50],"representation":[51],"of":[52,83],"already":[54],"trained":[55],"model.":[58],"Our":[59],"approach":[60],"employs":[61],"task-specific":[62],"loss":[63,82],"guidance":[64],"alongside":[65],"residual":[66],"vector":[67],"(RVQ)":[69],"losses,":[70],"providing":[71],"ultra-low":[72],"bitrates":[73,95],"(i.e.,":[74],"less":[75],"than":[76],"200":[77],"bps)":[78],"with":[79],"a":[80],"minimal":[81],"the":[84],"model":[86,97],"performance.":[87],"The":[88],"resulting":[89],"tokenizer":[90],"adaptable":[92],"to":[93],"sizes":[98],"flexible":[100],"deployment.":[101],"Evaluated":[102],"on":[103],"automatic":[104],"speech":[105],"recognition":[106],"classification,":[109],"our":[110],"demonstrates":[112],"its":[113],"efficacy":[114],"potential":[116],"broader":[118],"architectural":[121],"applicability":[122],"through":[123],"appropriate":[124],"regularization.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-11-14T00:00:00"}