Projects per year
Abstract
The use of context-dependent targets has become standard in hybrid DNN systems for automatic speech recognition. However, we argue that despite the use of state-tying, optimising to context-dependent targets can lead to over-fitting, and that discriminating between arbitrary tied context-dependent targets may not be optimal. We propose a multitask learning method where the network jointly predicts context-dependent and monophone targets. We evaluate the method on a large-vocabulary lecture recognition task and show that it yields relative improvements of 3-10% over baseline systems.
Original language | English |
---|---|
Title of host publication | Proc IEEE International Conference on Acoustics, Speech and Signal Processing |
Place of Publication | Brisbane, QLD, Australia |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 4290-4294 |
Number of pages | 5 |
ISBN (Electronic) | 978-1-4673-6997-8 |
DOIs | |
Publication status | Published - 6 Aug 2015 |
Event | 40th IEEE International Conference on Acoustics, Speech and Signal Processing - Brisbane Convention & Exhibition Centre, Brisbane, Australia Duration: 19 Apr 2015 → 24 Apr 2015 |
Conference
Conference | 40th IEEE International Conference on Acoustics, Speech and Signal Processing |
---|---|
Abbreviated title | ICASSP 2015 |
Country/Territory | Australia |
City | Brisbane |
Period | 19/04/15 → 24/04/15 |
Fingerprint
Dive into the research topics of 'Regularization of context-dependent deep neural networks with context-independent multi-task training'. Together they form a unique fingerprint.Projects
- 1 Finished
Profiles
-
Peter Bell
- School of Informatics - Personal Chair of Speech Technology
- Institute of Language, Cognition and Computation
- Centre for Speech Technology Research
- Language, Interaction, and Robotics
Person: Academic: Research Active