End-to-end Learning for Text and Speech

Quoc V. Le


In this talk, I will discuss our recent work on using neural networks for NLP and speech recognition tasks. Our work started with the sequence-to-sequence learning framework that can read a variable-length input sequence and produce a variable-length output sequence. The framework allows neural networks to be applied to new tasks in text and speech domains. I will talk about the implementation details and results of our implementation on machine translation, dialogue modeling, and speech recognition. We also find that unsupervised learning in our framework is simple, and improves the performance of our networks significantly.


Cite as

Le, Q.V. (2016) End-to-end Learning for Text and Speech. Proc. 9th ISCA Speech Synthesis Workshop, (abstract).

Bibtex
@inproceedings{Le2016,
author={Quoc V. Le},
title={End-to-end Learning for Text and Speech},
year=2016,
booktitle={9th ISCA Speech Synthesis Workshop}
}