Automatic speech recognition design modeling

Babu Rao K.; Mopuru B.; Jawarneh M.; Luis-Arias J.; Ajibade S.-S.M.; Prabhu P. · Conversational Artificial Intelligence (2024) · DOI: 10.1002/9781394200801.ch22

Resumen

The term "automatic speech recognition" refers to the procedure by which an auditory signal of spoken words can be converted into text. Voice recognition is another term that may be used to describe this process in its simplest form. The challenging nature of automatic speech or voice recognition by a computer system can be attributed to a variety of contributing factors. Variation in the source, variation in the auditory surroundings, variation in the speakers physical and emotional condition, variation in the speaking rate, and variance in the speakers socio-linguistic background are all examples of these elements. This article presents a feature selection and machine learning-based automatic speech recognition system. Noise from speech is removed using least mean square adaptive algorithm. Then, feature selection is performed using Relied algorithm. It helps in improving the classification accuracy. Classification is performed using SVM-RBF, BPNN, and naive Bayes algorithm.