PerformanceNet:
Score-to-Audio Music Generation with Multi-Band Convolutional Residual Network

Bryan Wang, Yi-Hsuan Yang. Published in AAAI '19 (Acceptance Rate: 16.2%, Oral Presentation: 6.4%)

We propose PerformanceNet, a deep convolutional model that learns in an end-to- end manner the score-to-audio mapping between a symbolic representation of music called the piano rolls and an audio representation of music called the spectrograms. The model consists of two subnets: the ContourNet, which uses a U-Net structure to learn the correspondence between piano rolls and spectrograms and to give an initial result; and the TextureNet, which further uses a multi-band residual network to refine the result by adding the spectral texture of overtones and timbre. We also present the result of a user study that shows our model achieves higher mean opinion score (MOS) in naturalness and emotional expressivity than a WaveNet-based model and two commercial sound libraries.

ActiveErgo:
Automatic and Personalized Ergonomics using Self-actuating Furniture

Yu-Chian Wu, Te-Yen Wu, Paul Taele, Bryan Wang, Jun-You Liu, PO-EN LAI, Pin-sung Ku, Mike Y. Chen Published in ACM CHI '18 (Acceptance Rate = 25.7%)

We present ActiveErgo, the first active approach to improving ergonomics by combining sensing and actuation of motorized furniture. Our prototype system uses Kinect for skeletal sensing and monitoring to determine the ideal furniture positions for each user, then uses a combination of automatic adjustment and live feedback to adjust the computer monitor, desk, and chair positions.

CircuitSense:
Automatic Sensing of Physical Circuits and Generation of Virtual Circuits to Support Software Tools

Te-Yen Wu, Bryan Wang, Jiun-Yu Lee, Hao-Ping Shen, Yu-Chian Wu, Yu-An Chen, Pin-Sung Ku, Ming-Wei Hsu, Yu-Chih Lin, Mike Y. Chen. Published in ACM UIST '17 (Acceptance Rate = 22.5%)

We present CircuitSense, a system that automatically recognizes the wires and electronic components placed on breadboards. It uses a combination of passive sensing and active probing to detect and generate the corresponding circuit representation in software in real-time. It also dramatically simplifies the sharing of circuit designs with online communities.

CircuitStack:
Supporting Rapid Prototyping and Evolution of Electronic Circuits

Chiuan Wang, Hsuan-Ming Yeh, Bryan Wang , Te-Yen Wu, Hsin-Ruey Tsai, Rong-Hao Liang, Yi-Ping Hung, Mike Y. Chen. Published in ACM UIST'16 (Acceptance Rate = 21%)

We present CircuitStack, a system that combines the flexibility of breadboarding with the correctness of printed circuits, for enabling rapid and extensible circuit construction. This hybrid system enables circuit reconfigurability, component reusability, and high efficiency at the early stage of prototyping development.


Honors and Awards

Best Talk Award, ACM UIST '16

- My talk for CircuitStack was chosen as the best paper presentation of UIST'16. I was later invited to present the paper at SIGGRAPH '17.

The James Dyson Award 2016, The Jamse Dyson Foundation.

- CircuitStack was selected as the National Runner-up (top 5 in Taiwan) and was listed in the World Finallist (top 60 in the world).

Second Prize, NTU CSIE Undergraduate Research Competition

- In my two-years participation, I won the Second Prize by CircuitStack, the Appier Best Potential Award by CircuitSense, as well as two-times people's choice Best Popular Award.

Appier Top Conference Scholarships, Appier. Inc

- The scholarship from Appier Inc. sponsored my trips for attending the SIGGRAPH '17 and UIST '17 conferences.

First Prize, NTU Intelligent Conversational Bot Competition

- In the course Intelligent Conversational Bot, my teammates and I developed a music domain chatbot and won the first prize in the final competition. [site]