{"id":"https://openalex.org/W4402111239","doi":"https://doi.org/10.21437/interspeech.2024-1559","title":"Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation","display_name":"Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111239","doi":"https://doi.org/10.21437/interspeech.2024-1559"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1559","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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/A5016567570","display_name":"Hanzhao Li","orcid":"https://orcid.org/0009-0005-3215-7517"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanzhao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009337933","display_name":"Liumeng Xue","orcid":"https://orcid.org/0000-0003-2815-8494"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liumeng Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072447806","display_name":"Haohan Guo","orcid":"https://orcid.org/0000-0002-3393-9984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haohan Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108604484","display_name":"Yuanjun Lv","orcid":"https://orcid.org/0009-0002-2272-9153"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanjun Lv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102788683","display_name":"Yunlin Chen","orcid":"https://orcid.org/0000-0001-7423-983X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunlin Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064463617","display_name":"Hao Yin","orcid":"https://orcid.org/0000-0002-8539-6512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100782898","display_name":"Zhifei Li","orcid":"https://orcid.org/0000-0003-1246-741X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhifei Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8875,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95700578,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3390","last_page":"3394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.907800018787384,"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":0.907800018787384,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.9069282412528992},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.8544971346855164},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.8302847146987915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.759276807308197},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.7051548957824707},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6981910467147827},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6111478805541992},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42727023363113403},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4032948911190033},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35817259550094604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17527973651885986},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.14936783909797668}],"concepts":[{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.9069282412528992},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8544971346855164},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8302847146987915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759276807308197},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.7051548957824707},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6981910467147827},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6111478805541992},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42727023363113403},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4032948911190033},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35817259550094604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17527973651885986},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.14936783909797668}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1559","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2110375858","https://openalex.org/W2060409740","https://openalex.org/W2159307410","https://openalex.org/W2370747337","https://openalex.org/W2014919663","https://openalex.org/W1542588102","https://openalex.org/W2496295964","https://openalex.org/W2151333624","https://openalex.org/W2020464095","https://openalex.org/W2336887028"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
