Combining connectionist multi-band and full-band probability streams for speech recognition of natural numbers.
Nikki MirghaforiNelson MorganPublished in: ICSLP (1998)
Keyphrases
- speech recognition
- multi band
- frequency band
- language model
- multispectral
- speech signal
- speech synthesis
- speech recognizer
- hidden markov models
- automatic speech recognition
- neural network
- pattern recognition
- speaker identification
- probability distribution
- noisy environments
- speech recognition technology
- speech recognition systems
- hyperspectral
- speaker independent
- low frequency
- conditional probabilities
- high frequency
- remote sensing
- machine learning
- transfer function
- audio visual
- subband
- image quality