Using multiple acoustic feature sets for speech recognition.
András ZolnayDaniil KocharovRalf SchlüterHermann NeyPublished in: Speech Commun. (2007)
Keyphrases
- speech recognition
- cepstral coefficients
- feature set
- speech recognition systems
- speaker independent
- speech recognizers
- hidden markov models
- speech signal
- language model
- feature selection
- automatic speech recognition
- speech synthesis
- speech recognizer
- pattern recognition
- classification accuracy
- acoustic models
- noisy environments
- speech recognition technology
- speaker identification
- audio signal
- mel frequency cepstral coefficients
- feature vectors
- structural features
- noisy speech
- acoustic features
- feature extraction
- signal to noise ratio
- neural network
- speaker recognition
- extracted features