Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems.
Mohammad Abd-Alrahman Mahmoud AbushariahRaja Noor AinonRoziati ZainuddinMoustafa ElshafeiOthman Omran KhalifaPublished in: ISSPA (2010)
Keyphrases
- speech corpus
- speech recognition
- speech signal
- automatic speech recognition systems
- automatic speech recognition
- speaker independent
- speech synthesis
- speaker identification
- speaker dependent
- hidden markov models
- vocal tract
- speech recognizer
- noisy environments
- broadcast news
- speech recognition systems
- pattern recognition
- neural network
- language model
- acoustic features
- non stationary
- mel frequency cepstral coefficients
- co occurrence
- bayesian networks
- feature selection