Introduction to speech recognition
This is an incremental educational introduction to speech recognition for beginners, with limited practical impact.
The paper tackled isolated word recognition by implementing a system that correctly classifies three words using a small database, achieving performance through speech modeling and established algorithms like dynamic time warping and nearest neighbor.
This document contains lectures and practical experimentations using Matlab and implementing a system which is actually correctly classifying three words (one, two and three) with the help of a very small database. To achieve this performance, it uses speech modeling specificities, powerful computer algorithms (dynamic time warping and Dijktra's algorithm) and machine learning (nearest neighbor). This document introduces also some machine learning evaluation metrics.