Efficient VQ-based MMSE estimation for robust speech recognition.
José A. GonzálezAntonio M. PeinadoAngel M. GomezJosé L. CarmonaJuan Andres Morales-CordovillaPublished in: ICASSP (2010)
Keyphrases
- speech recognition
- hidden markov models
- noisy environments
- language model
- vector quantization
- speech synthesis
- speech recognition technology
- speech understanding
- automatic speech recognition
- speaker recognition
- speech processing
- pattern recognition
- speaker identification
- speech retrieval
- speech recognizer
- speech recognizers
- image compression
- isolated word
- keyword spotting
- speech recognition systems
- speaker dependent
- machine learning
- audio visual speech recognition
- cepstral coefficients
- image coding
- multiscale
- computer vision