Abstract We explore using Convolutional Neural Networks (CNNs) for a small-footprint
keyword spotting (KWS) task. CNNs are attractive for KWS since they have been shown to …

The impressive gains in performance obtained using deep neural networks (DNNs) for
automatic speech recognition (ASR) have motivated the application of DNNs to other …

Deep learning (DL) is becoming an increasingly interesting and powerful machine learning
method with successful applications in many domains, such as natural language …

In this paper we present novel language-independent bottleneck (BN) feature extraction
framework. In our experiments we have used Multilingual Artificial Neural Network (ANN) …

Learned feature representations and sub-phoneme posteriors from Deep Neural Networks
(DNNs) have been used separately to produce significant performance gains for speaker …

It is generally believed that direct sequence-to-sequence (seq2seq) speech recognition
models are competitive with hybrid models only when a large amount of data, at least a …

This paper presents the application of Neural Network Bottleneck (BN) features in Language
Identification (LID). BN features are generally used for Large Vocabulary Speech …

In this paper, we propose a Convolutional Neural Network (CNN) based speaker recognition
model for extracting robust speaker embeddings. The embedding can be extracted …

In this paper, we present a novel pipelined near real-time speaker recognition architecture
that enhances the performance of speaker recognition by exploiting the advantages of …

Multilingual training of neural networks has proven to be simple yet effective way to deal with
multilingual training corpora. It allows to use several resources to jointly train a language …