Adaptive filter theory
Speech and Audio Signal Processing: Processing and Perception of Speech and Music
Speech and Audio Signal Processing: Processing and Perception of Speech and Music
Digital Signal Processing: A Practical Approach
Digital Signal Processing: A Practical Approach
Challenges in adopting speech recognition
Communications of the ACM - Multimodal interfaces that flex, adapt, and persist
| Hi-index | 0.00 |
Automatic speech recognition systems have the potential to make hard to understand speech more easily recognizable. Designing a system that recognizes impaired speech is more difficult than a system that recognizes normal speech. The Automatic Malay Speech Recognition for Speech Disorder System is able to recognized impaired Malay words spoken by people who suffer from dysarthria, a motor speech disorder resulting from neuron damage, characterized by poor communication. It is developed using techniques used for normal speech recognition but modified to cater for the speech impairment. A feature extraction technique based on the Mel Frequency Cepstrum Coefficient (MFCC) is used along with artificial intelligent algorithms to recognize the speech. In addition, novel pre-processing steps are required to segment the speech prior to recognition taking into account the speech irregularities. The system requires that the user is registered with the system and the system is then trained to accommodate the user speech pattern. The outputs of the system are the visual display of the corrected words uttered or synthesized audio version of the corrected words.