Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Stas Tiomkin"'
Publikováno v:
IEEE Access, Vol 12, Pp 58275-58287 (2024)
While recommender systems have become an integral component of the Web experience, their heavy reliance on user data raises privacy and security concerns. Substituting user data with synthetic data can address these concerns, but accurately replicati
Externí odkaz:
https://doaj.org/article/8cd3581cdfc244a08f541df60f6275ba
Publikováno v:
Physical Review Research, Vol 5, Iss 2, p 023085 (2023)
Reinforcement learning (RL) is an important field of research in machine learning that is increasingly being applied to complex optimization problems in physics. In parallel, concepts from physics have contributed to important advances in RL with dev
Externí odkaz:
https://doaj.org/article/b41a16137c454effa3dc7e40a0fd0b68
Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety. A recently developed theo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a69a5e204793290938af952d0f80a30
Publikováno v:
IEEE Transactions on Audio, Speech, and Language Processing. 19:1278-1288
Concatenative synthesis and statistical synthesis are the two main approaches to text-to-speech (TTS) synthesis. Concatenative TTS (CTTS) stores natural speech features segments, selected from a recorded speech database. Consequently, CTTS systems en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0206fb27e796cc7141445970d7343d01
https://doi.org/10.1109/tasl.2010.2089679
https://doi.org/10.1109/tasl.2010.2089679
Publikováno v:
IEEE Transactions on Audio, Speech, and Language Processing. 18:1077-1082
In statistical HMM-based text-to-speech systems (STTS), speech feature dynamics is modeled by first- and second-order feature frame differences, which, typically, do not satisfactorily represent frame to frame feature dynamics present in natural spee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cbc390d88ac3c9118cf604442023984b
https://doi.org/10.1109/tasl.2010.2040795
https://doi.org/10.1109/tasl.2010.2040795
Publikováno v:
CDC
We present an information-theoretically motivated method for dimensionality reduction and realization of linear dynamical systems. Given a linear system with Gaussian inputs, we apply the Information Bottleneck principle to construct a continuous ran
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fb8b5cc998a2f58921a764e263cef714
https://doi.org/10.1109/cdc.2015.7403120
https://doi.org/10.1109/cdc.2015.7403120
Autor:
David Malah, Stas Tiomkin
Publikováno v:
INTERSPEECH
In statistical TTS systems (STTS), speech features dynamics is modeled by firstand second-order feature frame differences, which, typically, do not satisfactorily represent frame to frame feature dynamics present in natural speech. The reduced dynami
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::682375cfbecb96567b62d87b6cf0a282
https://doi.org/10.21437/interspeech.2008-179
https://doi.org/10.21437/interspeech.2008-179