with inbound calls 8hrs/day. Supervised a 6-person team in the labeling of audio data, and improving the efficiency and accuracy of the process. Leading develop projects with NTU, NTHU, sinicaML Enginner in Cyberon Tech. (Speech recognition team) Develops acoustic model language/command adaptive training procedure for Key Word Spotting product DSpotter. Implemental projects in Vietnamese, Chinese, English, Taiwanese scenario. Publish 2024 Pantents (Asus) - Electronic Device for Lightweight Procedures Construction - Electronic Device for Component Customization 2021 IEEE/ACM Transaction: Speech Emotion Recognition Considering Nonverbal Vocalization in Affective Conversations 2019 IEEE ICASSP