Ming-Chun Wu

Learn More
This paper describes the algorithms used in a prototypical software system for automatic pronunciation assessment of Mandarin Chinese. The system uses Viterbi decoding to isolate each syllable and find the log probability of a given utterance based on HMM (Hidden Markov models). The isolated syllables are then sent to a GMM (Gaussian mixture model) for tone(More)
Most existing embedded networks require custom gateways and tools to connect to the Internet. IP provides end-to-end communication between devices, without intermediate protocol translation gateways. IP-based embedded networks will provide scalable and interoperable communication mechanism for embedded devices, and they can get access to the Internet(More)
Principal Component Analysis (PCA) is adopted in diverse areas including signal processing and machine leaning. However, the derived principal components, the linear combinations of the original variables, are hard to be interpreted in many applications especially the blind source separation. Therefore, we propose regularized PCA via hard thresholding such(More)
  • 1