Abstract Deep Neural Networks (DNN) are nothing but neural networks with many hidden
layers. DNNs are becoming popular in automatic speech recognition tasks which combines …

Abstract Time Delay Neural Networks (TDNNs), also known as onedimensional
Convolutional Neural Networks (1-d CNNs), are an efficient and well-performing neural …

In this paper we describe a method to perform sequencediscriminative training of neural
network acoustic models without the need for frame-level cross-entropy pre-training. We use …

Recurrent neural network architectures have been shown to efficiently model long term
temporal dependencies between acoustic events. However the training time of recurrent …

Lattice-rescoring is a common approach to take advantage of recurrent neural language
models in ASR, where a word-lattice is generated from 1st-pass decoding and the lattice is …

Multi-style training, using data which emulates a variety of possible test scenarios, is a
popular approach towards robust acoustic modeling. However acoustic models capable of …

This paper describes a new baseline system for automatic speech recognition (ASR) in the
CHiME-4 challenge to promote the development of noisy ASR in speech processing …

In this paper we describe an extension of the Kaldi software toolkit to support neural-based
language modeling, intended for use in automatic speech recognition (ASR) and related …

Modern wake word detection systems usually rely on neural networks for acoustic modeling.
Transformers has recently shown superior performance over LSTM and convolutional …

We propose two adaptation models for recurrent neural network language models
(RNNLMs) to capture topic effects and longdistance triggers for conversational automatic …