{"id":"https://openalex.org/W4402115964","doi":"https://doi.org/10.21437/interspeech.2024-590","title":"Genhancer: High-Fidelity Speech Enhancement via Generative Modeling on Discrete Codec Tokens","display_name":"Genhancer: High-Fidelity Speech Enhancement via Generative Modeling on Discrete Codec Tokens","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402115964","doi":"https://doi.org/10.21437/interspeech.2024-590"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-590","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-590","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":"conference-paper","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/A5004403714","display_name":"Haici Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haici Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859099","display_name":"Jiaqi Su","orcid":"https://orcid.org/0000-0001-6038-0808"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqi Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeyu Jin","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":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1170","last_page":"1174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9937999844551086,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9937999844551086,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9750999808311462,"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/T13289","display_name":"Infant Health and Development","score":0.9099000096321106,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7389211654663086},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6950367093086243},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.6019555330276489},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.544712483882904},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48939457535743713},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4519869089126587},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.43277496099472046},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4283643960952759},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3456766605377197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27923309803009033},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10036107897758484},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09759166836738586},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.061673879623413086},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.05954614281654358}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7389211654663086},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6950367093086243},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.6019555330276489},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.544712483882904},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48939457535743713},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4519869089126587},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.43277496099472046},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4283643960952759},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3456766605377197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27923309803009033},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10036107897758484},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09759166836738586},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.061673879623413086},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.05954614281654358}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-590","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-590","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W2363660481","https://openalex.org/W2159899134","https://openalex.org/W3211091508","https://openalex.org/W2136586452","https://openalex.org/W68492818","https://openalex.org/W2095829722"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":12}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}