255 citations · 780 across the 58 of their papers we have counts for
19 papers · 1 filter
Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners
Sarthak Yadav, Sergios Theodoridis, Lars Kai Hansen +1
In this work, we propose a Multi-Window Masked Autoencoder (MW-MAE) fitted with a novel Multi-Window Multi-Head Attention (MW-MHA) module that facilitates the modelling of local-gl…
Speech inpainting: Context-based speech synthesis guided by video
Juan F. Montesinos, Daniel Michelsanti, Gloria Haro +2
Audio and visual modalities are inherently connected in speech signals: lip movements and facial expressions are correlated with speech sounds. This motivates studies that incorpor…
Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining
Holger Severin Bovbjerg, Zheng-Hua Tan
Keyword Spotting (KWS) models are becoming increasingly integrated into various systems, e.g. voice assistants. To achieve satisfactory performance, these models typically rely on…
On Training Targets and Activation Functions for Deep Representation Learning in Text-Dependent Speaker Verification
Achintya kr. Sarkar, Zheng-Hua Tan
Deep representation learning has gained significant momentum in advancing text-dependent speaker verification (TD-SV) systems. When designing deep neural networks (DNN) for extract…
Deep Spoken Keyword Spotting: An Overview
Iván López-Espejo, Zheng-Hua Tan, John Hansen +1
Spoken keyword spotting (KWS) deals with the identification of keywords in audio streams and has become a fast-growing technology thanks to the paradigm shift introduced by deep le…
On TasNet for Low-Latency Single-Speaker Speech Enhancement
Morten Kolbæk, Zheng-Hua Tan, Søren Holdt Jensen +1
In recent years, speech processing algorithms have seen tremendous progress primarily due to the deep learning renaissance. This is especially true for speech separation where the…
Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification
Achintya Kumar Sarkar, Md Sahidullah, Zheng-Hua Tan
In this paper, we propose a novel method that trains pass-phrase specific deep neural network (PP-DNN) based auto-encoders for creating augmented data for text-dependent speaker ve…
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…
On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement
Morten Kolbæk, Zheng-Hua Tan, Søren Holdt Jensen +1
Many deep learning-based speech enhancement algorithms are designed to minimize the mean-square error (MSE) in some transform domain between a predicted and a target speech signal.…
Keyword Spotting for Hearing Assistive Devices Robust to External Speakers
Iván López-Espejo, Zheng-Hua Tan, Jesper Jensen
Keyword spotting (KWS) is experiencing an upswing due to the pervasiveness of small electronic devices that allow interaction with them via speech. Often, KWS systems are speaker-i…
rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method
Zheng-Hua Tan, Achintya kr. Sarkar, Najim Dehak
This paper presents an unsupervised segment-based method for robust voice activity detection (rVAD). The method consists of two passes of denoising followed by a voice activity det…
Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
Achintya kr. Sarkar, Zheng-Hua Tan, Hao Tang +2
There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for im…
On the Relationship Between Short-Time Objective Intelligibility and Short-Time Spectral-Amplitude Mean-Square Error for Speech Enhancement
Morten Kolbæk, Zheng-Hua Tan, Jesper Jensen
The majority of deep neural network (DNN) based speech enhancement algorithms rely on the mean-square error (MSE) criterion of short-time spectral amplitudes (STSA), which has no a…
Monaural Speech Enhancement using Deep Neural Networks by Maximizing a Short-Time Objective Intelligibility Measure
Morten Kolbæk, Zheng-Hua Tan, Jesper Jensen
In this paper we propose a Deep Neural Network (DNN) based Speech Enhancement (SE) system that is designed to maximize an approximation of the Short-Time Objective Intelligibility…
Joint Separation and Denoising of Noisy Multi-talker Speech using Recurrent Neural Networks and Permutation Invariant Training
Morten Kolbæk, Dong Yu, Zheng-Hua Tan +1
In this paper we propose to use utterance-level Permutation Invariant Training (uPIT) for speaker independent multi-talker speech separation and denoising, simultaneously. Specific…
Adversarial Network Bottleneck Features for Noise Robust Speaker Verification
Hong Yu, Zheng-Hua Tan, Zhanyu Ma +1
In this paper, we propose a noise robust bottleneck feature representation which is generated by an adversarial network (AN). The AN includes two cascade connected networks, an enc…
Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification
Achintya Kr. Sarkar, Zheng-Hua Tan
In this paper, we present a time-contrastive learning (TCL) based bottleneck (BN)feature extraction method for speech signals with an application to text-dependent (TD) speaker ver…
Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks
Morten Kolbæk, Dong Yu, Zheng-Hua Tan +1
In this paper we propose the utterance-level Permutation Invariant Training (uPIT) technique. uPIT is a practically applicable, end-to-end, deep learning based solution for speaker…
DNN Filter Bank Cepstral Coefficients for Spoofing Detection
Hong Yu, Zheng-Hua Tan, Zhanyu Ma +1
With the development of speech synthesis techniques, automatic speaker verification systems face the serious challenge of spoofing attack. In order to improve the reliability of sp…