AI Music and Software Engineering, Product Management

Speech/NLP/LLM processing

DL-based Indoor Acoustic Scene Analysis- Develop sound/speech event and localization detection using CRNN two-stage architecture- Develop room size estimation and speech source distance prediction with channel attention-based model- Apply remixing post-processing to enhance out-of-domain noisy speech in low SNR scenariosMicrophone Recorder Classification- Build as recorder corpus using Rasberry Pi and implement spectral feature analysis of microphone data- Adopt attention-based model to evaluate close/far-field sparse-data microphone identification- Improve unseen-device detection by Domain Adaptation and RIR Data Augmentation

Senior Digital Designer focusing on high speed SerDes DSP/PHY development (Algorithm -> RTL -> Silicon)- 5G wireless SerDes PHY and mixed-signal chip design- Ethernet high speed PHY/LDPC Development- Data Center Switch PHY development

- Emotion Based Automated AI Music Melody and Accompaniment Generation- Musical Tension Based Automated Music Accompaniment Generation with MIR Approach

- PCI-e RF RX High Speed Equalization (DFE) Development and Modeling- Analyzing error converging curve and optimizing parameters- New equalization algorithm exploring