Very deep convolutional networks for end-to-end speech recognition | IEEE Conference Publication | IEEE Xplore

Very deep convolutional networks for end-to-end speech recognition


Abstract:

Sequence-to-sequence models have shown success in end-to-end speech recognition. However these models have only used shallow acoustic encoder networks. In our work, we su...Show More

Abstract:

Sequence-to-sequence models have shown success in end-to-end speech recognition. However these models have only used shallow acoustic encoder networks. In our work, we successively train very deep convolutional networks to add more expressive power and better generalization for end-to-end ASR models. We apply network-in-network principles, batch normalization, residual connections and convolutional LSTMs to build very deep recurrent and convolutional structures. Our models exploit the spectral structure in the feature space and add computational depth without overfitting issues. We experiment with the WSJ ASR task and achieve 10.5% word error rate without any dictionary or language model using a 15 layer deep network.
Date of Conference: 05-09 March 2017
Date Added to IEEE Xplore: 19 June 2017
ISBN Information:
Electronic ISSN: 2379-190X
Conference Location: New Orleans, LA, USA

References

References is not available for this document.