Incorporating tone features to convolutional neural network to improve Mandarin/Thai speech recognition.
Xinhui HuMasahiro SaikoChiori HoriPublished in: APSIPA (2014)
Keyphrases
- speech recognition
- convolutional neural network
- speech recognition systems
- hidden markov models
- automatic speech recognition
- speaker independent
- speech synthesis
- language model
- cepstral coefficients
- pattern recognition
- speech processing
- speech recognizer
- noisy environments
- speech recognition technology
- speech retrieval
- speaker identification
- speech signal
- mel frequency cepstral coefficients
- face detection
- speaker dependent
- low level
- feature space