{"id":"https://openalex.org/W7166838889","doi":"https://doi.org/10.18653/v1/2026.findings-acl.442","title":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","display_name":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166838889","doi":"https://doi.org/10.18653/v1/2026.findings-acl.442"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.442","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.442","pdf_url":"https://aclanthology.org/2026.findings-acl.442.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.442.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139779886","display_name":"Jiacheng Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiacheng Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139774732","display_name":"Hongfei Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongfei Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085373820","display_name":"Xinyuan Song","orcid":"https://orcid.org/0009-0005-4209-5671"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyuan Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016831945","display_name":"Y. Alicia Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Y. Alicia Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136015592","display_name":"Yanfu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanfu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139786637","display_name":"Ashley Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashley Gao","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87463214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9102","last_page":"9124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9627000093460083,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9627000093460083,"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"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.005799999926239252,"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/T12488","display_name":"Mental Health via Writing","score":0.004800000227987766,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/artificial-neural-network","display_name":"Artificial neural network","score":0.35269999504089355},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34940001368522644},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32100000977516174},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.3025999963283539},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.298799991607666},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.2831999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7031999826431274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.644599974155426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40070000290870667},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.442","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.442","pdf_url":"https://aclanthology.org/2026.findings-acl.442.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.442","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.442","pdf_url":"https://aclanthology.org/2026.findings-acl.442.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166838889.pdf","grobid_xml":"https://content.openalex.org/works/W7166838889.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"speech":[1,7,36,72,80],"codecs":[2,18],"provide":[3],"discrete":[4],"representations":[5],"for":[6],"language":[8],"models,":[9],"but":[10],"emotional":[11,41],"cues":[12,67],"are":[13],"often":[14],"degraded":[15],"during":[16],"quantization.Existing":[17],"mainly":[19],"optimize":[20],"acoustic":[21],"reconstruction,":[22,73],"leaving":[23],"emotion":[24,74,84],"expressiveness":[25],"insufficiently":[26],"modeled":[27],"at":[28],"the":[29],"representation":[30],"level.We":[31],"propose":[32],"an":[33],"emotionguided":[34],"neural":[35],"codec":[37],"that":[38],"explicitly":[39],"preserves":[40],"information":[42],"while":[43],"maintaining":[44],"semantic":[45,61],"fidelity":[46],"and":[47,59,76,86],"prosodic":[48],"naturalness.Our":[49],"framework":[50],"combines":[51],"emotion-semantic":[52],"guided":[53],"latent":[54],"modulation,":[55],"relation-preserving":[56],"emotional-semantic":[57],"distillation,":[58],"emotionweighted":[60],"alignment":[62],"to":[63,79],"retain":[64],"emotionally":[65],"salient":[66],"under":[68],"compression.Extensive":[69],"evaluations":[70],"across":[71],"recognition,":[75],"downstream":[77],"text":[78],"generation":[81],"demonstrate":[82],"improved":[83],"consistency":[85],"perceptual":[87],"quality":[88],"without":[89],"sacrificing":[90],"content":[91],"accuracy.":[92]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}