When a mismatch can be good: large vocabulary speech recognition trained with idealized tandem features.
Arlo FariaNelson MorganPublished in: SAC (2008)
Keyphrases
- speech recognition
- speech recognition systems
- hidden markov models
- speech recognizer
- isolated word
- speech processing
- pattern recognition
- language model
- speech synthesis
- automatic speech recognition
- speech recognition technology
- speaker independent
- speech understanding
- speech signal
- noisy environments
- speaker identification
- feature extraction
- cepstral coefficients
- feature vectors
- mel frequency cepstral coefficients
- keyword spotting
- feature space
- speaker dependent
- speech recognizers
- information retrieval
- feature set
- classification accuracy
- probabilistic model
- training set
- speaker adaptation
- computer vision