7 papers
Improving Transformer-based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Heads
Ye-Rin Jeoung, Joon-Young Yang, Jeong-Hwan Choi +1
Transformer-based end-to-end neural speaker diarization (EEND) models utilize the multi-head self-attention (SA) mechanism to enable accurate speaker label prediction in overlapped…
Instance-level loss based multiple-instance learning framework for acoustic scene classification
Won-Gook Choi, Joon-Hyuk Chang, Jae-Mo Yang +1
In the acoustic scene classification (ASC) task, an acoustic scene consists of diverse sounds and is inferred by identifying combinations of distinct attributes among them. This st…
Task-specific Optimization of Virtual Channel Linear Prediction-based Speech Dereverberation Front-End for Far-Field Speaker Verification
Joon-Young Yang, Joon-Hyuk Chang
Developing a single-microphone speech denoising or dereverberation front-end for robust automatic speaker verification (ASV) in noisy far-field speaking scenarios is challenging. T…
Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach
Mun-Hak Lee, Joon-Hyuk Chang
The remarkable performance of the pre-trained language model (LM) using self-supervised learning has led to a major paradigm shift in the study of natural language processing. In l…
Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs
Jae-Hong Lee, Joon-Hyuk Chang
Attribution methods calculate attributions that visually explain the predictions of deep neural networks (DNNs) by highlighting important parts of the input features. In particular…
Augmenting Bottleneck Features of Deep Neural Network Employing Motor State for Speech Recognition at Humanoid Robots
Moa Lee, Joon Hyuk Chang
As for the humanoid robots, the internal noise, which is generated by motors, fans and mechanical components when the robot is moving or shaking its body, severely degrades the per…
Ensemble of Jointly Trained Deep Neural Network-Based Acoustic Models for Reverberant Speech Recognition
Jeehye Lee, Myungin Lee, Joon-Hyuk Chang
Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In or…