Title :
Adaptive WRLS-VFF for speech analysis
Author :
Childers, D.G. ; Principe, J.C. ; Ting, Y.T.
Author_Institution :
Dept. of Electr. Eng., Florida Univ., Gainesville, FL, USA
fDate :
5/1/1995 12:00:00 AM
Abstract :
The paper shows that an adaptive weighted recursive least squares algorithm with a variable forgetting factor (WRLS-VFF) will adjust the size of the data segment to be analyzed according to its time-varying characteristics, as during the transitions between vowels and consonants. The algorithm can accurately estimate the vocal tract formants, anti-formants, and their bandwidths, be used for glottal inverse filtering, perform voiced (V)/unvoiced (U)/silent (S) classification of speech segments, estimate the input excitation (either white noise or periodic pulse trains), and estimate the instant of glottal closure
Keywords :
adaptive estimation; adaptive filters; autoregressive moving average processes; least squares approximations; recursive estimation; recursive filters; speech processing; white noise; adaptive WRLS-VFF; adaptive weighted recursive least squares algorithm; anti-formants; bandwidths; consonants; data segment; glottal closure instant; glottal inverse filtering; input excitation; periodic pulse trains; silent classification; speech analysis; speech segments; time-varying characteristic; unvoiced classification; variable forgetting factor; vocal tract formants; voiced classification; vowels; white noise; Algorithm design and analysis; Bandwidth; Estimation error; Filtering algorithms; Gaussian noise; Least squares methods; Noise measurement; Parameter estimation; Speech analysis; Speech enhancement;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
