Title :
A model of dynamic auditory perception and its application to robust speech recognition
Author :
Strope, Brian ; Alwan, Abeer
Author_Institution :
Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
Abstract :
This paper derives a non-linear model of dynamic auditory perception. The model consists of a linear filter bank with carefully-parameterized logarithmic additive adaptation after each filter output. An extensive series of perceptual forward masking experiments, together with previously reported forward masking data, determine the model´s dynamic parameters. The model´s prediction error of forward masking data has a standard deviation of less than 3.3 dB across wide ranging frequencies, input levels, and probe delay times. We present an initial evaluation of the dynamic model as a front end for an isolated word recognition system, and show an improvement in the robustness to background noise when compared to MFCC and LPCC front ends
Keywords :
acoustic signal processing; adaptive filters; adaptive signal processing; band-pass filters; filtering theory; hearing; prediction theory; speech intelligibility; speech processing; speech recognition; LPCC front ends; MFCC front ends; background noise robustness; dynamic auditory perception; dynamic parameters; filter output; forward masking data; input levels; isolated word recognition system; linear filter bank; nonlinear model; parameterized logarithmic additive adaptation; perceptual forward masking experiments; prediction error; probe delay times; robust speech recognition; standard deviation; Auditory system; Delay; Filter bank; Mel frequency cepstral coefficient; Nonlinear filters; Predictive models; Probes; Psychoacoustic models; Robustness; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3192-3
DOI :
10.1109/ICASSP.1996.540284
