255 citations · 780 across the 58 of their papers we have counts for
22 papers · 1 filter
Joint Minimum Processing Beamforming and Near-end Listening Enhancement
Andreas J. Fuglsig, Jesper Jensen, Zheng-Hua Tan +3
We consider speech enhancement for signals picked up in one noisy environment that must be rendered to a listener in another noisy environment. For both far-end noise reduction and…
Leveraging Domain Features for Detecting Adversarial Attacks Against Deep Speech Recognition in Noise
Christian Heider Nielsen, Zheng-Hua Tan
In recent years, significant progress has been made in deep model-based automatic speech recognition (ASR), leading to its widespread deployment in the real world. At the same time…
Filterbank Learning for Noise-Robust Small-Footprint Keyword Spotting
Iván López-Espejo, Ram C. M. C. Shekar, Zheng-Hua Tan +2
In the context of keyword spotting (KWS), the replacement of handcrafted speech features by learnable features has not yielded superior KWS performance. In this study, we demonstra…
Improved disentangled speech representations using contrastive learning in factorized hierarchical variational autoencoder
Yuying Xie, Thomas Arildsen, Zheng-Hua Tan
Leveraging the fact that speaker identity and content vary on different time scales, \acrlong{fhvae} (\acrshort{fhvae}) uses different latent variables to symbolize these two attri…
Minimum Processing Near-end Listening Enhancement
Andreas Jonas Fuglsig, Jesper Jensen, Zheng-Hua Tan +3
The intelligibility and quality of speech from a mobile phone or public announcement system are often affected by background noise in the listening environment. By pre-processing t…
Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay
Claus Meyer Larsen, Peter Koch, Zheng-Hua Tan
Voice Activity Detection (VAD) is an important pre-processing step in a wide variety of speech processing systems. VAD should in a practical application be able to detect speech in…
Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective
Yuying Xie, Thomas Arildsen, Zheng-Hua Tan
Disentangled representation learning aims to extract explanatory features or factors and retain salient information. Factorized hierarchical variational autoencoder (FHVAE) present…
Complex Recurrent Variational Autoencoder with Application to Speech Enhancement
Yuying Xie, Thomas Arildsen, Zheng-Hua Tan
As an extension of variational autoencoder (VAE), complex VAE uses complex Gaussian distributions to model latent variables and data. This work proposes a complex recurrent VAE fra…
Joint Far- and Near-End Speech Intelligibility Enhancement based on the Approximated Speech Intelligibility Index
Andreas Jonas Fuglsig, Jan Østergaard, Jesper Jensen +3
This paper considers speech enhancement of signals picked up in one noisy environment which must be presented to a listener in another noisy environment. Recently, it has been show…
Improvement of Noise-Robust Single-Channel Voice Activity Detection with Spatial Pre-processing
Max Væhrens, Andreas Jonas Fuglsig, Anders Post Jacobsen +4
Voice activity detection (VAD) remains a challenge in noisy environments. With access to multiple microphones, prior studies have attempted to improve the noise robustness of VAD b…
INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing
Wei Rao, Yihui Fu, Yanxin Hu +11
The ConferencingSpeech 2021 challenge is proposed to stimulate research on far-field multi-channel speech enhancement for video conferencing. The challenge consists of two separate…
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…
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…
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…
Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect
Daniel Michelsanti, Zheng-Hua Tan, Sigurdur Sigurdsson +1
When speaking in presence of background noise, humans reflexively change their way of speaking in order to improve the intelligibility of their speech. This reflex is known as Lomb…
Effects of Lombard Reflex on the Performance of Deep-Learning-Based Audio-Visual Speech Enhancement Systems
Daniel Michelsanti, Zheng-Hua Tan, Sigurdur Sigurdsson +1
Humans tend to change their way of speaking when they are immersed in a noisy environment, a reflex known as Lombard effect. Current speech enhancement systems based on deep learni…
On Training Targets and Objective Functions for Deep-Learning-Based Audio-Visual Speech Enhancement
Daniel Michelsanti, Zheng-Hua Tan, Sigurdur Sigurdsson +1
Audio-visual speech enhancement (AV-SE) is the task of improving speech quality and intelligibility in a noisy environment using audio and visual information from a talker. Recentl…
Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
Daniel Michelsanti, Zheng-Hua Tan
Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated…