Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Faria, Arlo"'
Autor:
Janiczek, John, Chong, Dading, Dai, Dongyang, Faria, Arlo, Wang, Chao, Wang, Tao, Liu, Yuzong
A text-to-speech (TTS) model trained to reconstruct speech given text tends towards predictions that are close to the average characteristics of a dataset, failing to model the variations that make human speech sound natural. This problem is magnifie
Externí odkaz:
http://arxiv.org/abs/2408.15916
The "Switchboard benchmark" is a very well-known test set in automatic speech recognition (ASR) research, establishing record-setting performance for systems that claim human-level transcription accuracy. This work highlights lesser-known practical c
Externí odkaz:
http://arxiv.org/abs/2206.06192
Autor:
Faria, Arlo, Gelbart, David
To reduce inter-speaker variability, vocal tract length normalization (VTLN) is commonly used to transform acoustic features for automatic speech recognition (ASR). The warp factors used in this process are usually derived by maximum likelihood (ML)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______463::b89a9dd6feaa249f7e4311dc437ffd64
http://hdl.handle.net/1842/1042
http://hdl.handle.net/1842/1042
Publikováno v:
2013 IEEE Workshop on Automatic Speech Recognition & Understanding; 2013, p192-197, 6p
Autor:
Faria, Arlo, Morgan, Nelson
Publikováno v:
Proceedings of the 2008 ACM Symposium: Applied Computing; 3/16/2008, p1574-1577, 4p
Publikováno v:
Machine Learning for Multimodal Interaction (9783540325499); 2006, p285-293, 9p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
IEEE Transactions on Audio, Speech & Language Processing; Sep2009, Vol. 17 Issue 7, p1253-1262, 10p, 3 Diagrams, 13 Charts