Abstract

In recent few years, deep learning has fast growing in many fields as natural language processing, image recognition, handwriting recognition, computer vision, and speech recognition. Automatic speech recognition (ASR) is a technique that refers to translating spoken words from an acoustic waveform into a text equivalent to what the speaker says. More recently, the advances in deep learning can support ASR in improving the performance of systems accuracies. Arabic is a Semitic language, one of the oldest used and most communicated languages in the world. But, it least concentrated in the case of Arabic speech recognition and under-resourced languages. This paper presents a survey that focuses on an automatic speech recognition system based on isolating words technique for Arabic speech. It also highlights the facilities and tools for developing speech recognition systems. This work is intended to be a useful starting point for those who are interested in ASR.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call