Audio Signal Processing Using Time Domain Mel-Frequency Wavelet Coefficient
Rinku Sebastian, Simon O'Keefe, Martin Trefzer
TL;DR
The paper addresses the need for time-localized, perceptually aligned features in speech processing by proposing Time-domain Mel frequency Wavelet Coefficients (TMFWC), computed without heavy time-frequency conversions. TMFWC combines Mel-scale filtering with time-domain wavelet-inspired analysis, enabling efficient feature extraction suitable for reservoir computing, which provides a lightweight, memory-capable readout paradigm. The approach reduces computational burden while maintaining discriminative power, demonstrated on Ti-46 and Audio-MNIST with reservoir ensembles, and shows competitive performance for digit and speaker recognition. This work offers a practical path toward real-time, robust audio processing by integrating perceptual Mel-scale representation with time-localized analysis in the time domain. Key contribution lies in the TMFWC construction and its effective pairing with Reservoir Computing to achieve efficiency without sacrificing accuracy, making it attractive for low-latency speech applications.
Abstract
Extracting features from the speech is the most critical process in speech signal processing. Mel Frequency Cepstral Coefficients (MFCC) are the most widely used features in the majority of the speaker and speech recognition applications, as the filtering in this feature is similar to the filtering taking place in the human ear. But the main drawback of this feature is that it provides only the frequency information of the signal but does not provide the information about at what time which frequency is present. The wavelet transform, with its flexible time-frequency window, provides time and frequency information of the signal and is an appropriate tool for the analysis of non-stationary signals like speech. On the other hand, because of its uniform frequency scaling, a typical wavelet transform may be less effective in analysing speech signals, have poorer frequency resolution in low frequencies, and be less in line with human auditory perception. Hence, it is necessary to develop a feature that incorporates the merits of both MFCC and wavelet transform. A great deal of studies are trying to combine both these features. The present Wavelet Transform based Mel-scaled feature extraction methods require more computation when a wavelet transform is applied on top of Mel-scale filtering, since it adds extra processing steps. Here we are proposing a method to extract Mel scale features in time domain combining the concept of wavelet transform, thus reducing the computational burden of time-frequency conversion and the complexity of wavelet extraction. Combining our proposed Time domain Mel frequency Wavelet Coefficient(TMFWC) technique with the reservoir computing methodology has significantly improved the efficiency of audio signal processing.