activity
20182021
most citedScene-aware Far-field Automatic Speech Recognition

2 citations · 3 across the 4 of their papers we have counts for

collaborators

8 papers

eess.AS2021

Online Self-Attentive Gated RNNs for Real-Time Speaker Separation

Ori Kabeli, Yossi Adi, Zhenyu Tang +2

Deep neural networks have recently shown great success in the task of blind source separation, both under monaural and binaural settings. Although these methods were shown to produ…

eess.AS20211 cited

Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning

Rohith Aralikatti, Anton Ratnarajah, Zhenyu Tang +1

We present a novel approach that improves the performance of reverberant speech separation. Our approach is based on an accurate geometric acoustic simulator (GAS) which generates…

cs.SD2021

Point-based Acoustic Scattering for Interactive Sound Propagation via Surface Encoding

Hsien-Yu Meng, Zhenyu Tang, Dinesh Manocha

We present a novel geometric deep learning method to compute the acoustic scattering properties of geometric objects. Our learning algorithm uses a point cloud representation of ob…

eess.AS20212 cited

Scene-aware Far-field Automatic Speech Recognition

Zhenyu Tang, Dinesh Manocha

We propose a novel method for generating scene-aware training data for far-field automatic speech recognition. We use a deep learning-based estimator to non-intrusively compute the…

cs.SD2020

IR-GAN: Room Impulse Response Generator for Far-field Speech Recognition

Anton Ratnarajah, Zhenyu Tang, Dinesh Manocha

We present a Generative Adversarial Network (GAN) based room impulse response generator (IR-GAN) for generating realistic synthetic room impulse responses (RIRs). IR-GAN extracts a…

cs.SD2020

Learning Acoustic Scattering Fields for Dynamic Interactive Sound Propagation

Zhenyu Tang, Hsien-Yu Meng, Dinesh Manocha

We present a novel hybrid sound propagation algorithm for interactive applications. Our approach is designed for dynamic scenes and uses a neural network-based learned scattered fi…