Voice Quality Detection Based On Temporal And Spatial Features

More about the book

Focusing on the automatic identification of voice qualities, this book presents a technique that enhances speech recognition systems. It utilizes three key characteristics of speech signals: Zero Crossing Rate, Short Time Energy, and Fundamental Frequency. The effectiveness of the proposed algorithm is demonstrated through data from three different speakers, achieving an overall accuracy of 87.2%. This work highlights the potential for improved speech detection through advanced analysis of vocal attributes.