Experiments on ANN Based ASR Systems UsingLimited Arabic Vocabulary

摘要

In this paper we investigated Artificial Neural Networks (ANN) basedAutomatic Speech Recognition (ASR) by using limited Arabic vocabularycorpora. These limited Arabic vocabulary subsets are digits and vowels carried byspecific carrier words. In addition to this, Hidden Markov Model (HMM) basedASR systems are designed and compared to ANN based systems by using thesame corpora. All systems are isolated word speech recognizers. The ANN basedrecognition system achieved 99.5% correct digit recognition. On the other hand,the HMM based recognition system achieved 98.1% correct digit recognition.With vowels carrier words, the ANN based recognition system achieved 92.13%correct vowel recognition; but the HMM based recognition system achieved91.6% correct vowel recognition.