{"id":"https://openalex.org/W4385823460","doi":"https://doi.org/10.21437/interspeech.2023-1490","title":"Multi-mode Neural Speech Coding Based on Deep Generative Networks","display_name":"Multi-mode Neural Speech Coding Based on Deep Generative Networks","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823460","doi":"https://doi.org/10.21437/interspeech.2023-1490"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1490","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5003594370","display_name":"Wei Xiao","orcid":"https://orcid.org/0000-0002-4418-0555"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wei Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679522","display_name":"Wenzhe Liu","orcid":"https://orcid.org/0000-0002-0827-6883"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenzhe Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048359823","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-6245-2673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020510777","display_name":"Yupeng Shi","orcid":"https://orcid.org/0009-0001-8898-6278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yupeng Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026722702","display_name":"Yuyong Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuyong Kang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108230628","display_name":"Dan Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078353046","display_name":"Shidong Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shidong Shang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5003594370"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4232,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82481067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"819","last_page":"823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9710999727249146,"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":0.9710999727249146,"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":0.9696999788284302,"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/T11309","display_name":"Music and Audio Processing","score":0.9239000082015991,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7250556945800781},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5789648294448853},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5581454038619995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5375897884368896},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4556084871292114},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.44502803683280945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39445605874061584},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0710899829864502},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.05289784073829651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250556945800781},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5789648294448853},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5581454038619995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5375897884368896},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4556084871292114},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.44502803683280945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39445605874061584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0710899829864502},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.05289784073829651},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1490","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/W2386387936","https://openalex.org/W3156291593","https://openalex.org/W2368779261","https://openalex.org/W4220812973","https://openalex.org/W2778699561","https://openalex.org/W3198184493","https://openalex.org/W2383319832","https://openalex.org/W2606323037","https://openalex.org/W2346058735","https://openalex.org/W1629725936"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}