Feedback Connection for Deep Neural Network-Based Acoustic Modeling
Tran D, Delcroix M, Ogawa A, Hümmer C, Nakatani T (2017)
Publication Language: English
Publication Type: Conference contribution
Publication year: 2017
Pages Range: 5240-5244
Event location: New Orleans, LA
ISBN: 978-1-5090-4117-6
DOI: 10.1109/ICASSP.2017.7953156
Abstract
The use of auxiliary features is an effective way to improve the performance of deep neural network (DNN)-based acoustic models. Most approaches use auxiliary features that represent the speaker or the environment. These auxiliary features are usually computed independently of the acoustic model. This paper investigates a types of auxiliary features obtained from the output of a hidden layer that feeds back to the input layer of the network. Since the auxiliary features are extracted from the hidden layer of the network no external information is required such as the speaker or the environment. Experimentally, by forcing the extraction of the auxiliary features from the same networks, we can further improve the performance of the overall network and reduce the total number of parameters used. We tested this approach with different deep neural network architectures including: deep neural networks, convolutional neural networks and unfolded recurrent convolutional networks. We confirmed the effectiveness of this approach on the CHiME3 dataset.
Authors with CRIS profile
How to cite
APA:
Tran, D., Delcroix, M., Ogawa, A., Hümmer, C., & Nakatani, T. (2017). Feedback Connection for Deep Neural Network-Based Acoustic Modeling. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5240-5244). New Orleans, LA, US.
MLA:
Tran, Dung, et al. "Feedback Connection for Deep Neural Network-Based Acoustic Modeling." Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA 2017. 5240-5244.
BibTeX: Download