Timezone: »
Lying at the core of human intelligence, relational thinking is characterized by initially relying on innumerable unconscious percepts pertaining to relations between new sensory signals and prior knowledge, consequently becoming a recognizable concept or object through coupling and transformation of these percepts. Such mental processes are difficult to model in real-world problems such as in conversational automatic speech recognition (ASR), as the percepts (if they are modelled as graphs indicating relationships among utterances) are supposed to be innumerable and not directly observable. In this paper, we present a Bayesian nonparametric deep learning method called deep graph random process (DGP) that can generate an infinite number of probabilistic graphs representing percepts. We further provide a closed-form solution for coupling and transformation of these percept graphs for acoustic modeling. Our approach is able to successfully infer relations among utterances without using any relational data during training. Experimental evaluations on ASR tasks including CHiME-2 and CHiME-5 demonstrate the effectiveness and benefits of our method.
Author Information
Huang Hengguan (NUS)
Fuzhao Xue (National University of Singapore)
Hao Wang (MIT)
Dr. Hao Wang is currently an assistant professor in the department of computer science at Rutgers University. Previously he was a Postdoctoral Associate at the Computer Science & Artificial Intelligence Lab (CSAIL) of MIT, working with Dina Katabi and Tommi Jaakkola. He received his PhD degree from the Hong Kong University of Science and Technology, as the sole recipient of the School of Engineering PhD Research Excellence Award in 2017. He has been a visiting researcher in the Machine Learning Department of Carnegie Mellon University. His research focuses on statistical machine learning, deep learning, and data mining, with broad applications on recommender systems, healthcare, user profiling, social network analysis, text mining, etc. His work on Bayesian deep learning for recommender systems and personalized modeling has inspired hundreds of follow-up works published at top conferences such as AAAI, ICML, IJCAI, KDD, NIPS, SIGIR, and WWW. It has received over 1000 citations, becoming the most cited paper at KDD 2015. In 2015, he was awarded the Microsoft Fellowship in Asia and the Baidu Research Fellowship for his innovation on Bayesian deep learning and its applications on data mining and social network analysis.
Ye Wang (National University of Singapore)
More from the Same Authors
-
2023 : Towards Effective Data Poisoning for Imbalanced Classification »
Snigdha Sushil Mishra · Hao He · Hao Wang -
2023 Oral: Self-Interpretable Time Series Prediction with Counterfactual Explanations »
Jingquan Yan · Hao Wang -
2023 Poster: Taxonomy-Structured Domain Adaptation »
Tianyi Liu · Zihao Xu · Hao He · Guangyuan Hao · Guang-He Lee · Hao Wang -
2023 Poster: Robust Perception through Equivariance »
Chengzhi Mao · Lingyu Zhang · Abhishek Joshi · Junfeng Yang · Hao Wang · Carl Vondrick -
2023 Poster: Self-Interpretable Time Series Prediction with Counterfactual Explanations »
Jingquan Yan · Hao Wang -
2022 Poster: Domain Adaptation for Time Series Forecasting via Attention Sharing »
Xiaoyong Jin · Youngsuk Park · Danielle Robinson · Hao Wang · Yuyang Wang -
2022 Spotlight: Domain Adaptation for Time Series Forecasting via Attention Sharing »
Xiaoyong Jin · Youngsuk Park · Danielle Robinson · Hao Wang · Yuyang Wang -
2021 Poster: STRODE: Stochastic Boundary Ordinary Differential Equation »
Huang Hengguan · Hongfu Liu · Hao Wang · Chang Xiao · Ye Wang -
2021 Poster: Correcting Exposure Bias for Link Recommendation »
Shantanu Gupta · Hao Wang · Zachary Lipton · Yuyang Wang -
2021 Spotlight: Correcting Exposure Bias for Link Recommendation »
Shantanu Gupta · Hao Wang · Zachary Lipton · Yuyang Wang -
2021 Spotlight: STRODE: Stochastic Boundary Ordinary Differential Equation »
Huang Hengguan · Hongfu Liu · Hao Wang · Chang Xiao · Ye Wang -
2021 Poster: Delving into Deep Imbalanced Regression »
Yuzhe Yang · Kaiwen Zha · YINGCONG CHEN · Hao Wang · Dina Katabi -
2021 Oral: Delving into Deep Imbalanced Regression »
Yuzhe Yang · Kaiwen Zha · YINGCONG CHEN · Hao Wang · Dina Katabi