Projects per year
Abstract
In this work, we implement a deep belief network for the acoustic-articulatory inversion mapping problem. We find that adding up to 3 hidden-layers improves inversion accuracy. We also show that this improvement is due to the higher ex- pressive capability of a deep model and not a consequence of adding more adjustable parameters. Additionally, we show unsupervised pretraining of the sys- tem improves its performance in all cases, even for a 1 hidden-layer model. Our implementation obtained an average root mean square error of 0.95 mm on the MNGU0 test dataset, beating all previously published results.
Original language | English |
---|---|
Title of host publication | Proc. NIPS 2011 Workshop on Deep Learning and Unsupervised Feature Learning |
Publication status | Published - Dec 2011 |
Fingerprint
Dive into the research topics of 'A Deep Neural Network for Acoustic-Articulatory Speech Inversion'. Together they form a unique fingerprint.Projects
- 2 Finished
-
Deep Learning for Speech Recognition
Murray, I. (Principal Investigator) & Renals, S. (Co-investigator)
UK industry, commerce and public corporations
1/10/11 → 31/03/15
Project: Research
-
ULTRAX: Ultrax: Real-time tongue tracking for speech therapy using ultrasound
Richmond, K. (Principal Investigator), Renals, S. (Co-investigator), Cleland, J. (Co-Investigator (External)) & Scobbie, J. M. (Co-Investigator (External))
1/02/11 → 31/07/14
Project: Research