# A network of deep neural networks for distant speech recognition

## TL;DR

This paper introduces a novel deep neural network architecture for distant speech recognition that jointly trains and communicates between modules, improving robustness under challenging acoustic conditions.

## Contribution

It proposes a fully communicative, jointly trained network of DNNs for speech enhancement and recognition, addressing their independent training limitations.

## Key findings

- Outperforms recent joint training approaches.
- Effective under various datasets and acoustic conditions.
- Enhances robustness in adverse environments.

## Abstract

Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and reverberation are met. A prominent limitation of current systems lies in the lack of matching and communication between the various technologies involved in the distant speech recognition process. The speech enhancement and speech recognition modules are, for instance, often trained independently. Moreover, the speech enhancement normally helps the speech recognizer, but the output of the latter is not commonly used, in turn, to improve the speech enhancement. To address both concerns, we propose a novel architecture based on a network of deep neural networks, where all the components are jointly trained and better cooperate with each other thanks to a full communication scheme between them. Experiments, conducted using different datasets, tasks and acoustic conditions, revealed that the proposed framework can overtake other competitive solutions, including recent joint training approaches.