195 citations · 227 across the 10 of their papers we have counts for
10 papers
Blind Deconvolution of Binary and Pattern Images with Pixel Intensity Constraints and Sparse Gradient Prior
Qinghua Zhang, Xuesong Yang, Liangtian He +2
Blind image deconvolution (BID) is a prominent research topic in the field of imaging sciences, given its significant practical applications. Most existing model-based BID methods…
REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling
Hu Hu, Xuesong Yang, Zeynab Raeesy +6
Accents mismatching is a critical problem for end-to-end ASR. This paper aims to address this problem by building an accent-robust RNN-T system with domain adversarial training (DA…
AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
Kaizhi Qian, Yang Zhang, Shiyu Chang +2
Non-parallel many-to-many voice conversion, as well as zero-shot voice conversion, remain under-explored areas. Deep style transfer algorithms, such as generative adversarial netwo…
When CTC Training Meets Acoustic Landmarks
Di He, Xuesong Yang, Boon Pang Lim +3
Connectionist temporal classification (CTC) provides an end-to-end acoustic model (AM) training strategy. CTC learns accurate AMs without time-aligned phonetic transcription, but s…
Improved ASR for Under-Resourced Languages Through Multi-Task Learning with Acoustic Landmarks
Di He, Boon Pang Lim, Xuesong Yang +2
Furui first demonstrated that the identity of both consonant and vowel can be perceived from the C-V transition; later, Stevens proposed that acoustic landmarks are the primary cue…
Deep Learning Based Speech Beamforming
Kaizhi Qian, Yang Zhang, Shiyu Chang +3
Multi-channel speech enhancement with ad-hoc sensors has been a challenging task. Speech model guided beamforming algorithms are able to recover natural sounding speech, but the sp…
Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
Xuesong Yang, Kartik Audhkhasi, Andrew Rosenberg +3
The performance of automatic speech recognition systems degrades with increasing mismatch between the training and testing scenarios. Differences in speaker accents are a significa…
Acoustic Landmarks Contain More Information About the Phone String than Other Frames for Automatic Speech Recognition with Deep Neural Network Acoustic Model
Di He, Boon Pang Lim, Xuesong Yang +2
Most mainstream Automatic Speech Recognition (ASR) systems consider all feature frames equally important. However, acoustic landmark theory is based on a contradictory idea, that s…
End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager
Xuesong Yang, Yun-Nung Chen, Dilek Hakkani-Tur +4
Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utteranc…
Landmark-based consonant voicing detection on multilingual corpora
Xiang Kong, Xuesong Yang, Mark Hasegawa-Johnson +2
This paper tests the hypothesis that distinctive feature classifiers anchored at phonetic landmarks can be transferred cross-lingually without loss of accuracy. Three consonant voi…