{"id":"https://openalex.org/W4297841734","doi":"https://doi.org/10.21437/interspeech.2022-443","title":"Vector-quantized Variational Autoencoder for Phase-aware Speech Enhancement","display_name":"Vector-quantized Variational Autoencoder for Phase-aware Speech Enhancement","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841734","doi":"https://doi.org/10.21437/interspeech.2022-443"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-443","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-443","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10119/18157","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083304186","display_name":"Tuan Vu Ho","orcid":"https://orcid.org/0000-0001-6819-0443"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tuan Vu Ho","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779631","display_name":"Quoc Huy Nguyen","orcid":"https://orcid.org/0000-0001-5676-9028"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quoc Huy Nguyen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083304186"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3648,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51164987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9641000032424927,"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":0.948199987411499,"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/autoencoder","display_name":"Autoencoder","score":0.9256770014762878},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5909313559532166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.563498318195343},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.46386685967445374},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4454006850719452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3381546139717102},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.23262956738471985},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15460830926895142},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09075671434402466},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.06681305170059204}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9256770014762878},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5909313559532166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.563498318195343},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.46386685967445374},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4454006850719452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3381546139717102},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.23262956738471985},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15460830926895142},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09075671434402466},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.06681305170059204}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-443","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-443","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01333:0005685413","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/18157","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proc. InterSpeech 2022","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01333:0005685413","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/18157","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proc. InterSpeech 2022","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4220775285","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
