We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of phonemes. The alignment between the input and output sequences is established using an attention mechanism: the decoder emits each symbol based on a context created with a subset of input symbols elected by the attention mechanism. We report initial results demonstrating that this new approach achieves phoneme error rates that are comparable to the state-of-the-art HMM-based decoders, on the TIMIT dataset.
@article{arxiv.1412.1602,
title = {End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results},
author = {Jan Chorowski and Dzmitry Bahdanau and Kyunghyun Cho and Yoshua Bengio},
journal= {arXiv preprint arXiv:1412.1602},
year = {2014}
}
Comments
As accepted to: Deep Learning and Representation Learning Workshop, NIPS 2014