The tradeoff between time and frequency resolution is viewed as the fundamental difference between conventional spectrographic analysis and cochlear signal processing for broadband, rapid-changing signals. The model's response exhibits a wavelet-like analysis in the scale domain that preserves good temporal resolution; the frequency of each spectral component in a broadband signal can be accurately determined from the interpeak intervals in the instantaneous firing rates of auditory fibers. Such properties of the cochlear model are demonstrated with natural speech and synthetic complex signals. 1 Introduction As a nonparametric tool, spectrogram, or short-term Fourier transform, is widely used in analyzing non-stationary signals, such speech. Usually a window is applied to the running signal and then the Fourier transform is performed. The specific window applied determines the tradeoff between temporal and spectral resolutions of the analysis, as indicated by the uncertainty principle [1].

The tradeoff between time and frequency resolution is viewed as the fundamental difference between conventional spectrographic analysis and cochlear signal processing for broadband, rapid-changing signals. The model's response exhibits a wavelet-like analysis in the scale domain that preserves good temporal resolution; the frequency of each spectral component in a broadband signal can be accurately determined from the interpeak intervals in the instantaneous firing rates of auditory fibers. Such properties of the cochlear model are demonstrated with natural speech and synthetic complex signals. 1 Introduction As a nonparametric tool, spectrogram, or short-term Fourier transform, is widely used in analyzing non-stationary signals, such speech. Usually a window is applied to the running signal and then the Fourier transform is performed. The specific window applied determines the tradeoff between temporal and spectral resolutions of the analysis, as indicated by the uncertainty principle [1].

Fourier transform, is widely used in analyzing non-stationary signals, such speech.

Compensatory information is available from the visual speech signals around the speaker's mouth. Previous attempts at using these visual speech signals to improve automatic speech recognition systems have combined the acoustic and visual speech information at a symbolic level using heuristic rules. In this paper, we demonstrate an alternative approach to fusing the visual and acoustic speech information by training feedforward neural networks to map the visual signal onto the corresponding short-term spectral amplitude envelope (STSAE) of the acoustic signal. This information can be directly combined with the degraded acoustic STSAE. Significant improvements are demonstrated in vowel recognition from noise-degraded acoustic signals. These results are compared to the performance of humans, as well as other pattern matching and estimation algorithms. 1 INTRODUCTION

Previous attempts at using these visual speech signals to improve automatic speech recognition systems havecombined the acoustic and visual speech information at a symbolic level using heuristic rules. In this paper, we demonstrate an alternative approach to fusing the visual and acoustic speech information by training feedforward neural networks to map the visual signal onto the corresponding short-term spectral amplitude envelope (STSAE) of the acoustic signal. This information can be directly combined with the degraded acoustic STSAE. Significant improvementsare demonstrated in vowel recognition from noise-degraded acoustic signals. These results are compared to the performance of humans, as well as other pattern matching and estimation algorithms. 1 INTRODUCTION Current automatic speech recognition systems rely almost exclusively on the acoustic speechsignal, and as a consequence, these systems often perform poorly in noisy Combining Visual and Acoustic Speech Signals 233 environments.