255 citations · 780 across the 58 of their papers we have counts for
15 papers · 1 filter
Vocal Tract Length Perturbation for Text-Dependent Speaker Verification with Autoregressive Prediction Coding
Achintya kr. Sarkar, Zheng-Hua Tan
In this letter, we propose a vocal tract length (VTL) perturbation method for text-dependent speaker verification (TD-SV), in which a set of TD-SV systems are trained, one for each…
Assessing Wireless Sensing Potential with Large Intelligent Surfaces
Cristian J. Vaca-Rubio, Pablo Ramirez-Espinosa, Kimmo Kansanen +3
Sensing capability is one of the most highlighted new feature of future 6G wireless networks. This paper addresses the sensing potential of Large Intelligent Surfaces (LIS) in an e…
CC-Loss: Channel Correlation Loss For Image Classification
Zeyu Song, Dongliang Chang, Zhanyu Ma +2
The loss function is a key component in deep learning models. A commonly used loss function for classification is the cross entropy loss, which is a simple yet effective applicatio…
Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
Jiyang Xie, Zhanyu Ma, and Jianjun Lei +4
Due to lack of data, overfitting ubiquitously exists in real-world applications of deep neural networks (DNNs). We propose advanced dropout, a model-free methodology, to mitigate o…
Audio-Visual Speech Inpainting with Deep Learning
Giovanni Morrone, Daniel Michelsanti, Zheng-Hua Tan +1
In this paper, we present a deep-learning-based framework for audio-visual speech inpainting, i.e., the task of restoring the missing parts of an acoustic speech signal from reliab…
An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation
Daniel Michelsanti, Zheng-Hua Tan, Shi-Xiong Zhang +4
Speech enhancement and speech separation are two related tasks, whose purpose is to extract either one or more target speech signals, respectively, from a mixture of sounds generat…
UIAI System for Short-Duration Speaker Verification Challenge 2020
Md Sahidullah, Achintya Kumar Sarkar, Ville Vestman +5
In this work, we present the system description of the UIAI entry for the short-duration speaker verification (SdSV) challenge 2020. Our focus is on Task 1 dedicated to text-depend…
Data augmentation enhanced speaker enrollment for text-dependent speaker verification
Achintya Kumar Sarkar, Himangshu Sarma, Priyanka Dwivedi +1
Data augmentation is commonly used for generating additional data from the available training data to achieve a robust estimation of the parameters of complex models like the one f…
A Primer on Large Intelligent Surface (LIS) for Wireless Sensing in an Industrial Setting
Cristian J. Vaca-Rubio, Pablo Ramirez-Espinosa, Robin Jess Williams +4
One of the beyond-5G developments that is often highlighted is the integration of wireless communication and radio sensing. This paper addresses the potential of communication-sens…
Exploring Filterbank Learning for Keyword Spotting
Iván López-Espejo, Zheng-Hua Tan, Jesper Jensen
Despite their great performance over the years, handcrafted speech features are not necessarily optimal for any particular speech application. Consequently, with greater or lesser…
On Bottleneck Features for Text-Dependent Speaker Verification Using X-vectors
Achintya Kumar Sarkar, Zheng-Hua Tan
Applying x-vectors for speaker verification has recently attracted great interest, with the focus being on text-independent speaker verification. In this paper, we study x-vectors…
OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
Xiaoxu Li, Dongliang Chang, Zhanyu Ma +5
A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data. To mitigate overfitting…
Vocoder-Based Speech Synthesis from Silent Videos
Daniel Michelsanti, Olga Slizovskaia, Gloria Haro +3
Both acoustic and visual information influence human perception of speech. For this reason, the lack of audio in a video sequence determines an extremely low speech intelligibility…
A Multi-view Perspective of Self-supervised Learning
Chuanxing Geng, Zhenghao Tan, Songcan Chen
As a newly emerging unsupervised learning paradigm, self-supervised learning (SSL) recently gained widespread attention, which usually introduces a pretext task without manual anno…
Relaxed N-Pairs Loss for Context-Aware Recommendations of Television Content
Miklas S. Kristoffersen, Sven E. Shepstone, Zheng-Hua Tan
This paper studies context-aware recommendations in the television domain by proposing a deep learning-based method for learning joint context-content embeddings (JCCE). The method…