Researchers have shown a great deal of interest in automatic speech recognition within the past ten years. Even if suggested strategies have helped several applications in daily life, more techniques are still needed for new applications. With the use of automatic voice recognition technology, devices may translate speech signals into words, sentences, or orders. People’s way of life has changed because of the embedded technology’s quick growth and widespread application in everyday life. The application of speech recognition technologies to embedded devices is bound to become popular. The goal of automated speech recognition (ASR) study is to get to the point where a computer can accurately identify every word that is spoken by any person in real-time, regardless of noise levels, speaker attributes, accents, or channel conditions. Human supervision is used during the training process to produce transcriptions of voice utterances by automatic speech recognition systems.