Learning Shared Encoding Representation for End-to-End Speech Recognition Models
arXiv:1904.02147
Abstract
In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that the multi-task training not only tackles the complexity of optimizing CTC models such as acoustic-to-word but also results in significant improvement compared to the plain-task training with an optimal setup. Furthermore, we propose to use the encoding representation learned by the multi-task network to initialize the encoder of attention-based models. Thereby, we train a deep attention-based end-to-end model with 10 long short-term memory (LSTM) layers of encoder which produces 12.2\% and 22.6\% word-error-rate on Switchboard and CallHome subsets of the Hub5 2000 evaluation.
arXiv admin note: substantial text overlap with arXiv:1902.01951
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Improving neural networks by preventing co-adaptation of feature detectors
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- Attention-Based Models for Speech Recognition
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Improved training of end-to-end attention models for speech recognition
- A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
- Advances in All-Neural Speech Recognition
- Direct Acoustics-to-Word Models for English Conversational Speech Recognition
- Deep-FSMN for Large Vocabulary Continuous Speech Recognition