الفهرس Only 14 pages are availabe for public view
 |  | from | 86 |  |  |
| | | from | 86 | | |
Abstract
Automatic Speech Recognition (ASR) is a technology that allows a computer to identify the words that a person speaks into a microphone or telephone. HTK (Hidden Markov models Toolkit) is used to build the speech recognition engine. This thesis presents an evaluation for using different acoustic units in automatic speech recognition (ASR). Comparative experiments have indicated that the use of syllables as acoustic units leads to an improvement in the recognition performance of HMM-based ASR systems in noisy and clean environments. A series of experiments on speaker-independent continuous-speech recognition have been carried out using subsets of the noisy speech corpus AURORA and Arabic speech data. The obtained results show that syllable-based recognition outperformed word-based recognition and triphone-based recognition in noisy and clean environments. The use of syllables did not only improve the performance of the ASR process in noisy environments, but it also limited the complexity of the computation (and consequently the running time) of the recognition process. This is due to the limited number of the syllables that has been used for the ASR compared to the number of words and triphones that represents the vocabulary of AURORA and Arabic speech data. In the future, we will compare and contrast different methods of speech recognition systems for Arabic speech.