Add to ORKG• Implement a high-accuracy text-dependent/short-duration speaker id system • Exploit Deep Neural Networks (DNNs) ability to model speech signals [1] • Explore new features for speaker verification •Compare/Combine classical and DNN systems 2 DNN as a Feature Extractor (-30/+10) window of 40-d mel-filterbank energies. d-vectors are the accumulated activations from the last hidden layer. 4 full connected maxout hidden layers (256 nodes). The last two layers drop 0.5 activations. Layer removed for training and evaluation of speakers
The speech signal conveys information about the identity of the speaker. The area of speaker identif...
This paper explores three novel approaches to improve the performance of speaker verification (SV) s...
This paper presents an improved deep embedding learning method based on convolutional neural network...
In this paper we investigate the use of deep neural networks (DNNs) for a small footprint text-depen...
Deep learning and neural network research has grown significantly in the fields of automatic speech ...
This paper explores novel ideas in building end-to-end deep neural network (DNN) based text-dependen...
International audienceSpeaker verification (SV) suffers from unsatisfactory performance in far-field...
\Lambda, sundarg.iitm.ernet.in Abstract In this paper, we propose two neural network-based approache...
The objective of this work is to study state-of-the-art deep neural networks based speaker verificat...
We propose a Deep Neural Network (DNN)-based Speaker Verification (SV) system using features derived...
This study aims is to establish a small system of text-independent recognition of speakers for a rel...
We examine the use of Deep Neural Networks (DNN) in extracting Baum-Welch statistics for i-vector-ba...
Speaker identification techniques are one of those most advanced modern technologies and there are m...
The recent speaker embeddings framework has been shown to provide excellent performance on the task ...
The aim of this work is to gain insights into how the deep neural network (DNN) models should be tra...
The speech signal conveys information about the identity of the speaker. The area of speaker identif...
This paper explores three novel approaches to improve the performance of speaker verification (SV) s...
This paper presents an improved deep embedding learning method based on convolutional neural network...
In this paper we investigate the use of deep neural networks (DNNs) for a small footprint text-depen...
Deep learning and neural network research has grown significantly in the fields of automatic speech ...
This paper explores novel ideas in building end-to-end deep neural network (DNN) based text-dependen...
International audienceSpeaker verification (SV) suffers from unsatisfactory performance in far-field...
\Lambda, sundarg.iitm.ernet.in Abstract In this paper, we propose two neural network-based approache...
The objective of this work is to study state-of-the-art deep neural networks based speaker verificat...
We propose a Deep Neural Network (DNN)-based Speaker Verification (SV) system using features derived...
This study aims is to establish a small system of text-independent recognition of speakers for a rel...
We examine the use of Deep Neural Networks (DNN) in extracting Baum-Welch statistics for i-vector-ba...
Speaker identification techniques are one of those most advanced modern technologies and there are m...
The recent speaker embeddings framework has been shown to provide excellent performance on the task ...
The aim of this work is to gain insights into how the deep neural network (DNN) models should be tra...
The speech signal conveys information about the identity of the speaker. The area of speaker identif...
This paper explores three novel approaches to improve the performance of speaker verification (SV) s...
This paper presents an improved deep embedding learning method based on convolutional neural network...