Deep Learning Based Natural Language Processing for End to End Speech Translation

TL;DR

This paper reviews deep learning techniques for end-to-end speech translation, focusing on signal processing and deep recurrent neural networks to improve speech-to-text systems in NLP.

Contribution

It presents an overview of applying deep learning and signal processing methods to develop efficient speech-to-text translation systems.

Findings

Deep learning enhances speech translation accuracy.

Recurrent neural networks effectively model sequential speech data.

Signal processing techniques improve system robustness.

Abstract

Deep Learning methods employ multiple processing layers to learn hierarchial representations of data. They have already been deployed in a humongous number of applications and have produced state-of-the-art results. Recently with the growth in processing power of computers to be able to do high dimensional tensor calculations, Natural Language Processing (NLP) applications have been given a significant boost in terms of efficiency as well as accuracy. In this paper, we will take a look at various signal processing techniques and then application of them to produce a speech-to-text system using Deep Recurrent Neural Networks.