Haoran Sun

Haoran Sun

Auto-generated profile, based on publicly available information

Haoran Sun

BNRist, Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 March 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HSHaoran Sun
Haoran Sun
DWDong Wang
Dong Wang
LLLantian LI
Lantian LI
CCChen Chen
Chen Chen
TZThomas Fang Zheng
Thomas Fang Zheng
Speech disentanglement aims to decompose independent causal factors of speech signals into separate codes. Perfect disentanglement benefits to a broad range of speech processing tasks. This paper presents a simple but effective disentanglement approach based on cycle consistency loss and random factor substitution. This leads to a novel random cycle (RC) loss that enforces analysis-and-resynthesis consistency, a main principle of reductionism. We theoretically demonstrate that the proposed RC loss can achieve independent codes if well optimized, which in turn leads to superior disentanglement when combined with information bottleneck (IB). Extensive simulation experiments were conducted to understand the properties of the RC loss, and experimental results on voice conversion further demonstrate the practical merit of the proposal. Source code and audio samples can be found on the webpage http://rc.cslt.org .

3 November 2021 in arXiv
Verified
Preprint
Open access
PDF file
XCXinshi Chen
Xinshi Chen
HSHaoran Sun
Haoran Sun
CECaleb Ellington
Caleb Ellington
EXEric Xing
Eric Xing
LSLe Song
Le Song
We consider the problem of discovering $K$ related Gaussian directed acyclic graphs (DAGs), where the involved graph structures share a consistent causal order and sparse unions of supports. Under the multi-task learning setting, we propose a $l_1/l_2$-regularized maximum likelihood estimator (MLE) for learning $K$ linear structural equation models. We theoretically show that the joint estimator, by leveraging data across related tasks, can achieve a better sample complexity for recovering the causal order (or topological order) than separate estimations. Moreover, the joint estimator is able to recover non-identifiable DAGs, by estimating them together with some identifiable DAGs. Lastly, our analysis also shows the consistency of union support recovery of the structures. To allow practical implementation, we design a continuous optimization problem whose optimizer is the same as the joint estimator and can be approximated efficiently by an iterative algorithm. We validate the theoretical analysis and the effectiveness of the joint estimator in experiments.