Skills
Expertise:
- Modeling and customization of Automatic Speech Recognition (ASR)
- Modeling and detection of paralinguistic information (i.e. emotion, health condition, speaker ID and traits) from speech
- Machine learning for speech signal (Winner of 3 Interspeech speaker trait challenges)
- Modeling and measurement of speech production with applications to recognition and clinical assessment of speech
- Multimodal signal processing, image processing and imaging applications
- Robust ASR, Biometrics
- Experiences on KALDI, Tensorflow, PyTorch, Keras, HTK, MITLM, Thrax, Phonetisaurus, Sequitur, Attila, Festival, HTS, Praat, openSMILE, LaTex, SPSS
- Experiences on ASR using KALDI, deep neural network using KALDI, phone recognition using HTK, acoustic feature extraction using Praat scripts and openSMILE
- Programming: Python, C++, Linux shell script, Matlab, Octave
- Operating systems: Linux, OSX
- Language: Korean (Native), English (Fluent)