Formant Estimation

Illustrates an algorithm for estimating the locations of the formants of voiced speech intervals

Speech processing designates a team consisting of Prof. Lawrence Rabiner (Rutgers University and University of California, Santa Barbara), Prof. Ronald Schafer (Stanford University), Kirty Vedula and Siva Yedithi (Rutgers University). This exercise is one of a set of speech processing exercises that are intended to supplement the teaching material in the textbook “Theory and Applications of Digital Speech Processing” by L R Rabiner and R W Schafer.
This MATLAB exercise illustrates an algorithm for estimating the locations of the formants of voiced speech intervals based on the locations of the speech polynomial roots as obtained from a frame-based analysis of a speech signal using the method of Linear Prediction Analysis. A key aspect of this algorithm is finding regions of quasi-contiguous speech frames (where the first three formants form a contiguous region over the duration of the voiced region), and then extending these regions (both backward and forward) based on a somewhat weaker criterion for contiguous behavior of the formants