17 citations · 21 across the 5 of their papers we have counts for
5 papers
Corrupting Data to Remove Deceptive Perturbation: Using Preprocessing Method to Improve System Robustness
Hieu Le, Hans Walker, Dung Tran +1
Although deep neural networks have achieved great performance on classification tasks, recent studies showed that well trained networks can be fooled by adding subtle noises. This…
Augmented Contrastive Self-Supervised Learning for Audio Invariant Representations
Melikasadat Emami, Dung Tran, Kazuhito Koishida
Improving generalization is a major challenge in audio classification due to labeled data scarcity. Self-supervised learning (SSL) methods tackle this by leveraging unlabeled data…
Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features
Trung Dang, Dung Tran, Peter Chin +1
Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data.…
An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions
Aswin Shanmugam Subramanian, Xiaofei Wang, Shinji Watanabe +3
Sequence-to-sequence (S2S) modeling is becoming a popular paradigm for automatic speech recognition (ASR) because of its ability to jointly optimize all the conventional ASR compon…
Speaker Selective Beamformer with Keyword Mask Estimation
Yusuke Kida, Dung Tran, Motoi Omachi +2
This paper addresses the problem of automatic speech recognition (ASR) of a target speaker in background speech. The novelty of our approach is that we focus on a wakeup keyword, w…