Nonlinear scale decomposition based features for visual speech recognition
作者： J. Andrew Bangham , Richard Harvey , Iain Matthews , Stephen Cox
DOI: 10.5281/ZENODO.36896
关键词:
摘要: A mathematical morphology based filter structure called a sieve is used to process mouth image sequences of talker's and form visual speech features. The effects varying the type filter, post-processing hidden Markov model (HMM) parameters on recognition accuracy are investigated using two audio-visual databases.
sci-hub.st 参考文章(0)