Journal
EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING
Volume -, Issue -, Pages -Publisher
SPRINGER
DOI: 10.1186/s13636-018-0141-9
Keywords
Speech recognition; End-to-end; Transfer learning
Categories
Funding
- National Natural Science Foundation of China [61673395, 61403415]
- Natural Science Foundation of Henan Province [162300410331]
Ask authors/readers for more resources
A transfer learning-based end-to-end speech recognition approach is presented in two levels in our framework. Firstly, a feature extraction approach combining multilingual deep neural network (DNN) training with matrix factorization algorithm is introduced to extract high-level features. Secondly, the advantage of connectionist temporal classification (CTC) is transferred to the target attention-based model through a joint CTC-attention model composed of shallow recurrent neural networks (RNNs) on top of the proposed features. The experimental results show that the proposed transfer learning approach achieved the best performance among all end-to-end methods and could be comparable to the state-of-the-art speech recognition system for TIMIT when further jointly decoded with a RNN language model.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available