Topology combined machine learning for consonant recognition
Here, we provide a transparent and broadly applicable methodology, TopCap, to capture the most salient topological features inherent in time series for machine learning. Notably, in classifying voiced and voiceless consonants, TopCap achieves an accuracy exceeding 96% and is geared towards designing topological convolutional layers for deep learning of speech and audio signals. Availible on arXiv at arxiv.org/abs/2311.15210. Visit here for more information.