Template-based spectral estimation using microphone array for speech recognition.
Satoshi TamuraEriko HishikawaWataru TaguchiSatoru HayamizuPublished in: INTERSPEECH (2010)
Keyphrases
- speech recognition
- spectral estimation
- minimum variance
- power spectrum
- signal processing
- pattern recognition
- hidden markov models
- language model
- synthetic aperture radar
- speech signal
- speech recognition technology
- speech synthesis
- speech recognition systems
- fourier transform
- automatic speech recognition
- sar imagery
- speech recognizer
- noisy environments
- speaker independent
- image reconstruction
- speaker identification
- frequency domain
- natural images
- neural network