[PDF][PDF] Convolutional neural networks for small-footprint keyword spotting.
TN Sainath, C Parada - Interspeech, 2015 - isca-archive.org
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 …
keyword spotting (KWS) task. CNNs are attractive for KWS since they have been shown to …
Deep neural network approaches to speaker and language recognition
F Richardson, D Reynolds… - IEEE signal processing …, 2015 - ieeexplore.ieee.org
The impressive gains in performance obtained using deep neural networks (DNNs) for
automatic speech recognition (ASR) have motivated the application of DNNs to other …
automatic speech recognition (ASR) have motivated the application of DNNs to other …
A review on deep learning approaches in speaker identification
SS Tirumala, SR Shahamiri - … of the 8th international conference on …, 2016 - dl.acm.org
Deep learning (DL) is becoming an increasingly interesting and powerful machine learning
method with successful applications in many domains, such as natural language …
method with successful applications in many domains, such as natural language …
The language-independent bottleneck features
In this paper we present novel language-independent bottleneck (BN) feature extraction
framework. In our experiments we have used Multilingual Artificial Neural Network (ANN) …
framework. In our experiments we have used Multilingual Artificial Neural Network (ANN) …
A unified deep neural network for speaker and language recognition
Learned feature representations and sub-phoneme posteriors from Deep Neural Networks
(DNNs) have been used separately to produce significant performance gains for speaker …
(DNNs) have been used separately to produce significant performance gains for speaker …
Single headed attention based sequence-to-sequence model for state-of-the-art results on switchboard
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 …
models are competitive with hybrid models only when a large amount of data, at least a …
[PDF][PDF] Neural Network Bottleneck Features for Language Identification.
This paper presents the application of Neural Network Bottleneck (BN) features in Language
Identification (LID). BN features are generally used for Large Vocabulary Speech …
Identification (LID). BN features are generally used for Large Vocabulary Speech …
Frame-level speaker embeddings for text-independent speaker recognition and analysis of end-to-end model
In this paper, we propose a Convolutional Neural Network (CNN) based speaker recognition
model for extracting robust speaker embeddings. The embedding can be extracted …
model for extracting robust speaker embeddings. The embedding can be extracted …
A near real-time automatic speaker recognition architecture for voice-based user interface
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 …
that enhances the performance of speaker recognition by exploiting the advantages of …
Multilingually trained bottleneck features in spoken language recognition
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 …
multilingual training corpora. It allows to use several resources to jointly train a language …