Densely Connected Convolutional Networks for Speech Recognition

08/10/2018
by   Chia Yu Li, et al.
0

This paper presents our latest investigation on Densely Connected Convolutional Networks (DenseNets) for acoustic modelling (AM) in automatic speech recognition. DenseN-ets are very deep, compact convolutional neural networks, which have demonstrated incredible improvements over the state-of-the-art results on several data sets in computer vision. Our experimental results show that DenseNet can be used for AM significantly outperforming other neural-based models such as DNNs, CNNs, VGGs. Furthermore, results on Wall Street Journal revealed that with only a half of the training data DenseNet was able to outperform other models trained with the full data set by a large margin.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/19/2021

Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition

We investigate densely connected convolutional networks (DenseNets) and ...
research
10/15/2019

Analyzing Large Receptive Field Convolutional Networks for Distant Speech Recognition

Despite significant efforts over the last few years to build a robust au...
research
11/28/2017

Exploiting Nontrivial Connectivity for Automatic Speech Recognition

Nontrivial connectivity has allowed the training of very deep networks b...
research
12/29/2017

The CAPIO 2017 Conversational Speech Recognition System

In this paper we show how we have achieved the state-of-the-art performa...
research
12/17/2018

Fully Convolutional Speech Recognition

Current state-of-the-art speech recognition systems build on recurrent n...
research
04/05/2019

Jasper: An End-to-End Convolutional Neural Acoustic Model

In this paper, we report state-of-the-art results on LibriSpeech among e...
research
02/04/2022

Polyphonic pitch detection with convolutional recurrent neural networks

Recent directions in automatic speech recognition (ASR) research have sh...

Please sign up or login with your details

Forgot password? Click here to reset