Title :
A blind algorithm for recovering articulator positions from acoustics
Author_Institution :
Comput. & Comput. Sci. Div., Los Alamos Nat. Lab., Los Alamos, NM, USA
Abstract :
MIMICRI is a signal-processing algorithm that has been shown to blindly infer and invert memoryless nonlinear functions of unobservable bandlimited signals, such as the mapping from the unobservable positions of the speech articulators to observable speech sounds. We review results of using MIMICRI on toy problems and on human speech data. We note that MIMICRI requires that the user specify two parameters: the dimensionality and pass-band of the unobservable signals. We show how to use cross-validation to help estimate the passband. An unexpected consequence of this work is that it helps separate signals with overlapping frequency bands.
Keywords :
speech processing; MIMICRI; acoustics; articulator positions; blind algorithm; human speech data; memoryless nonlinear functions; observable speech sounds; signal processing; speech articulators; unobservable bandlimited signals; Acoustic measurements; Computational modeling; Cutoff frequency; Inverse problems; Laboratories; Microphones; Nonlinear acoustics; Position measurement; Speech; Vectors;
Conference_Titel :
Signals, Systems and Computers, 2009 Conference Record of the Forty-Third Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
978-1-4244-5825-7
DOI :
10.1109/ACSSC.2009.5469740
