Simplified End-to-End MMI Training and Voting for ASR
arXiv:1703.10356
Abstract
A simplified speech recognition system that uses the maximum mutual information (MMI) criterion is considered. End-to-end training using gradient descent is suggested, similarly to the training of connectionist temporal classification (CTC). We use an MMI criterion with a simple language model in the training stage, and a standard HMM decoder. Our method compares favorably to CTC in terms of performance, robustness, decoding time, disk footprint and quality of alignments. The good alignments enable the use of a straightforward ensemble method, obtained by simply averaging the predictions of several neural network models, that were trained separately end-to-end. The ensemble method yields a considerable reduction in the word error rate.
References in corpus (9)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Achieving Human Parity in Conversational Speech Recognition
- Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
- Residual Convolutional CTC Networks for Automatic Speech Recognition
- Towards better decoding and language model integration in sequence to sequence models
- Deep Recurrent Neural Networks for Acoustic Modelling
- Personalized Speech recognition on mobile devices
- The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image Classification