{"id":"https://openalex.org/W4415898421","doi":"https://doi.org/10.18653/v1/2026.acl-long.138","title":"SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization","display_name":"SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415898421","doi":"https://doi.org/10.18653/v1/2026.acl-long.138"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.138","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.138","pdf_url":"https://aclanthology.org/2026.acl-long.138.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.138.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082539414","display_name":"Wenxi Chen","orcid":"https://orcid.org/0000-0001-9329-7277"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ruiqi Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiqi Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yushen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yushen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108896784","display_name":"Zhikang Niu","orcid":"https://orcid.org/0009-0002-2709-9381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhikang Niu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ziyang Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104326367","display_name":"Xiquan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiquan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114117046","display_name":"Yuzhe Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuzhe Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wenhanlin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhanlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shunshun Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shunshun Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ming Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748253","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0001-5338-8166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329117","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-5801-2571"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie Chen","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":0.01787884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3030","last_page":"3048"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6636000275611877,"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":0.6636000275611877,"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":0.13740000128746033,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06710000336170197,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8072999715805054},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.692300021648407},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4417000114917755},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.39980000257492065},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.39410001039505005},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.36959999799728394},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3612000048160553}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8072999715805054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.792900025844574},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.692300021648407},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6676999926567078},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3587000072002411},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.34540000557899475},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.3018999993801117},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.25440001487731934},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.138","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.138","pdf_url":"https://aclanthology.org/2026.acl-long.138.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.16841","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.16841","pdf_url":"https://arxiv.org/pdf/2510.16841","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,"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.2510.16841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.16841","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.138","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.138","pdf_url":"https://aclanthology.org/2026.acl-long.138.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3278014984","display_name":null,"funder_award_id":"U23B2018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415898421.pdf","grobid_xml":"https://content.openalex.org/works/W4415898421.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Wenxi":[0],"Chen,":[1,5],"Ruiqi":[2],"Yan,":[3],"Yushen":[4],"Zhikang":[6],"Niu,":[7],"Ziyang":[8],"Ma,":[9],"Xiquan":[10],"Li,":[11],"Yuzhe":[12],"Liang,":[13],"Wenhanlin,":[14],"Shunshun":[15],"Yin,":[16],"Ming":[17],"Tao,":[18],"Xinsheng":[19],"Wang,":[20],"Xie":[21],"Chen.":[22],"Proceedings":[23],"of":[24,29],"the":[25,30],"64th":[26],"Annual":[27],"Meeting":[28],"Association":[31],"for":[32],"Computational":[33],"Linguistics":[34],"(Volume":[35],"1:":[36],"Long":[37],"Papers).":[38],"2026.":[39]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-22T00:00:00"}
