{"id":"https://openalex.org/W4416513971","doi":"https://doi.org/10.18653/v1/2026.acl-long.423","title":"XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs","display_name":"XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416513971","doi":"https://doi.org/10.18653/v1/2026.acl-long.423"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.423","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.423","pdf_url":"https://aclanthology.org/2026.acl-long.423.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.423.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yitian Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yitian Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016171406","display_name":"Jin Li","orcid":"https://orcid.org/0000-0001-6887-7720"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luozhijie Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kuangwei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuangwei Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101708792","display_name":"Dong Zhang","orcid":"https://orcid.org/0000-0002-6379-0244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ruifan Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruifan Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaogui Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaogui Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327351","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0001-7712-8668"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhaoye Fei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoye Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004651932","display_name":"Qinyuan Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinyuan Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622912","display_name":"Shimin Li","orcid":"https://orcid.org/0000-0003-0216-2639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shimin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019571252","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0009-0004-9578-9696"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xipeng Qiu","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":0.02708207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9350","last_page":"9369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8449000120162964,"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":0.8449000120162964,"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":0.07490000128746033,"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":0.012500000186264515,"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/codec","display_name":"Codec","score":0.8179000020027161},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.47429999709129333},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45899999141693115},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45669999718666077},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4174000024795532},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33059999346733093},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.31769999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425999879837036},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8179000020027161},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6050999760627747},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45899999141693115},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4174000024795532},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3889000117778778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31769999861717224},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.3041999936103821},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.2736999988555908},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2662000060081482}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.423","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.423","pdf_url":"https://aclanthology.org/2026.acl-long.423.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:2506.23325","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23325","pdf_url":"https://arxiv.org/pdf/2506.23325","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.2506.23325","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.23325","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.423","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.423","pdf_url":"https://aclanthology.org/2026.acl-long.423.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416513971.pdf","grobid_xml":"https://content.openalex.org/works/W4416513971.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Yitian":[0],"Gong,":[1],"Luozhijie":[2],"Jin,":[3],"Kuangwei":[4],"Chen,":[5],"Dong":[6],"Zhang,":[7,13],"Ruifan":[8],"Deng,":[9],"Xiaogui":[10],"Yang,":[11],"Xin":[12],"Zhaoye":[14],"Fei,":[15],"Qinyuan":[16],"Cheng,":[17],"Shimin":[18],"Li,":[19],"Xipeng":[20],"Qiu.":[21],"Proceedings":[22],"of":[23,28],"the":[24,29],"64th":[25],"Annual":[26],"Meeting":[27],"Association":[30],"for":[31],"Computational":[32],"Linguistics":[33],"(Volume":[34],"1:":[35],"Long":[36],"Papers).":[37],"2026.":[38]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}