VLSI Architecture of GMM Processing and Viterbi Decoder for 60, 000-Word Real-Time Continuous Speech Recognition.
Hiroki NoguchiKazuo MiuraTsuyoshi FujinagaTakanobu SugaharaHiroshi KawaguchiMasahiko YoshimotoPublished in: IEICE Trans. Electron. (2011)
Keyphrases
- vlsi architecture
- real time
- continuous speech recognition
- low complexity
- vlsi implementation
- low power
- gaussian mixture model
- hidden markov models
- low cost
- low density parity check
- n gram
- multiscale
- computational complexity
- error concealment
- distributed video coding
- noisy channel
- neural network
- image processing
- computer vision