and question set for HMM-based singing voice synthesis
Sinsy is a HMM-based singing voice synthesis system
His research interests include statistical approaches to speech processing such as voice transformation, speech synthesis, speech production, speech analysis, and speech recognition.
Voice Demos - HMM/DNN-based speech synthesis system …
He has been working on speech and language processing. He led the TTS R&D work and built TTS systems for various local languages (English, Chinese, Malay, etc) on various platforms (Cloud, PC, Smartphone, etc). He also worked in projects on speech recognition, speaker/language recognition, computer aided language learning, natural language processing, transliteration, sentiment analysis, parsing, language model, semantics, etc. Recently, he is leading the research of natural language understanding for voice synthesis, deep learning technologies for language processing, personalized and expressive speech synthesis, automated corpus annotation, etc.