An exploration of semi-supervised and language-adversarial transfer learning using hybrid acoustic model for hindi speech recognition
- 8 April 2021
- journal article
- research article
- Published by Springer Nature in Journal of Reliable Intelligent Environments
- Vol. 8 (2) , 117-132
Abstract
No abstract availableKeywords
This publication has 65 references indexed in Scilit:
- Librispeech: An ASR corpus based on public domain audio books2015
- Speech acoustic modeling from raw multichannel waveforms2015
- On the Properties of Neural Machine Translation: Encoder–Decoder Approaches2014
- Multilingual acoustic models using distributed deep neural networks2013
- Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions2013
- Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers2013
- The language-independent bottleneck features2012
- Study of probabilistic and Bottle-Neck features in multilingual environment2011
- Performance evaluation of sequentially combined heterogeneous feature streams for Hindi speech recognition systemTelecommunication Systems, 2011
- Long Short-Term MemoryNeural Computation, 1997