Deep-Sparse-Representation-Based Features for Speech Recognition.
Pulkit SharmaVinayak AbrolAnil Kumar SaoPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2017)
Keyphrases
- speech recognition
- speech recognition systems
- hidden markov models
- speech signal
- speech recognizer
- feature space
- cepstral coefficients
- automatic speech recognition
- speech synthesis
- feature vectors
- language model
- noisy environments
- pattern recognition
- speech recognition technology
- speech understanding
- speech processing
- handwriting recognition
- feature set
- classification accuracy
- speaker independent
- em algorithm
- mel frequency cepstral coefficients
- low level
- neural network
- speech recognizers