Abstract
Natural language communication between humans and machines is a popular direction of artificial intelligence. As a technology for realizing direct dialogue between humans and machines, speech recognition technology can convert human speech signals into language information, providing technical support for human-machine language communication. In this paper, we conduct a speech recognition study. First, we collect more than 1,000 pieces of speech data, preprocess the speech data, extract three different characteristics of speech such as LPC, LPCC, and MFCC, and divide the speech data into a training set and a test set. Two naive Bayesian and KNN classifiers are used for classification, and the classification accuracy is obtained. This paper mainly studies the accuracy of isolated word recognition in three different features and two different classification algorithms.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have