J
Jorge Chang
Researcher at Ohio State University
Publications - 6
Citations - 160
Jorge Chang is an academic researcher from Ohio State University. The author has contributed to research in topics: Speaker recognition & Gaussian process. The author has an hindex of 4, co-authored 6 publications receiving 73 citations.
Papers
More filters
Journal ArticleDOI
Robust Speaker Recognition Based on Single-Channel and Multi-Channel Speech Enhancement
TL;DR: Systematic evaluations and comparisons on the NIST SRE 2010 retransmitted corpus show that both monaural and multi-channel speech enhancement significantly outperform x-vector's performance, and the covariance matrix estimate is effective for the MVDR beamformer.
Journal ArticleDOI
Toward autonomous additive manufacturing: Bayesian optimization on a 3D printer
James R. Deneault,Jorge Chang,Jay Myung,Daylond Hooper,Andrew Armstrong,Mark A. Pitt,Benji Maruyama +6 more
TL;DR: The Additive Manufacturing Autonomous Research System (AM ARES) as discussed by the authors is a research robot that uses an online Bayesian optimizer for multi-dimensional optimization of print parameters to accelerate materials discovery and development.
Journal ArticleDOI
Efficient Closed-loop Maximization of Carbon Nanotube Growth Rate using Bayesian Optimization.
Jorge Chang,Pavel Nikolaev,Pavel Nikolaev,Jennifer Carpena-Núñez,Rahul Rao,Kevin Decker,Ahmad E. Islam,Jiseob Kim,Mark A. Pitt,Jay I. Myung,Benji Maruyama +10 more
TL;DR: A promising application of BO is demonstrated in CNT synthesis as an efficient and robust algorithm which can improve the growth rate of CNT in the BO-planner experiments over the seed experiments up to a factor 8 and rapidly improve its predictive power.
Proceedings ArticleDOI
Robust speaker recognition based on DNN/i-vectors and speech separation
Jorge Chang,DeLiang Wang +1 more
TL;DR: This study investigates a phonetically-aware i-vector system in noisy conditions and proposes a front-end to tackle the noise problem by performing speech separation and examines its performance for both verification and identification tasks.
Journal ArticleDOI
Data-driven experimental design and model development using Gaussian process with active learning.
TL;DR: The Gaussian Process with Active Learning (GPAL) as discussed by the authors is an extension of the parametric, adaptive design optimization (ADO) framework, which combines Gaussian processes with active learning to iteratively fit the model and use it to optimize the design selection throughout the experiment.