Target Speaker Extraction under Noisy Underdetermined Conditions Using Conditional Variational Autoencoder, Global Style Token, and Neural Postfilter
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Now Publishers
2025-01-01
|
| Series: | APSIPA Transactions on Signal and Information Processing |
| Online Access: | http://www.nowpublishers.com/article/Details/SIP-20240067 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832584072270970880 |
|---|---|
| author | Rui Wang Takuya Fujimura Tomoki Toda |
| author_facet | Rui Wang Takuya Fujimura Tomoki Toda |
| author_sort | Rui Wang |
| collection | DOAJ |
| format | Article |
| id | doaj-art-6efc91925d1b4b9d8bc1550ec025108e |
| institution | Kabale University |
| issn | 2048-7703 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Now Publishers |
| record_format | Article |
| series | APSIPA Transactions on Signal and Information Processing |
| spelling | doaj-art-6efc91925d1b4b9d8bc1550ec025108e2025-01-27T18:43:46ZengNow PublishersAPSIPA Transactions on Signal and Information Processing2048-77032025-01-0114110.1561/116.20240067Target Speaker Extraction under Noisy Underdetermined Conditions Using Conditional Variational Autoencoder, Global Style Token, and Neural PostfilterRui WangTakuya FujimuraTomoki Todahttp://www.nowpublishers.com/article/Details/SIP-20240067 |
| spellingShingle | Rui Wang Takuya Fujimura Tomoki Toda Target Speaker Extraction under Noisy Underdetermined Conditions Using Conditional Variational Autoencoder, Global Style Token, and Neural Postfilter APSIPA Transactions on Signal and Information Processing |
| title | Target Speaker Extraction under Noisy Underdetermined Conditions Using Conditional Variational Autoencoder, Global Style Token, and Neural Postfilter |
| title_full | Target Speaker Extraction under Noisy Underdetermined Conditions Using Conditional Variational Autoencoder, Global Style Token, and Neural Postfilter |
| title_fullStr | Target Speaker Extraction under Noisy Underdetermined Conditions Using Conditional Variational Autoencoder, Global Style Token, and Neural Postfilter |
| title_full_unstemmed | Target Speaker Extraction under Noisy Underdetermined Conditions Using Conditional Variational Autoencoder, Global Style Token, and Neural Postfilter |
| title_short | Target Speaker Extraction under Noisy Underdetermined Conditions Using Conditional Variational Autoencoder, Global Style Token, and Neural Postfilter |
| title_sort | target speaker extraction under noisy underdetermined conditions using conditional variational autoencoder global style token and neural postfilter |
| url | http://www.nowpublishers.com/article/Details/SIP-20240067 |
| work_keys_str_mv | AT ruiwang targetspeakerextractionundernoisyunderdeterminedconditionsusingconditionalvariationalautoencoderglobalstyletokenandneuralpostfilter AT takuyafujimura targetspeakerextractionundernoisyunderdeterminedconditionsusingconditionalvariationalautoencoderglobalstyletokenandneuralpostfilter AT tomokitoda targetspeakerextractionundernoisyunderdeterminedconditionsusingconditionalvariationalautoencoderglobalstyletokenandneuralpostfilter |