Harmonicity Plays a Critical Role in DNN Based Versus in Biologically-Inspired Monaural Speech Segregation Systems. (arXiv:2203.04420v1 [eess.AS])

Recent advancements in deep learning have led to drastic improvements in
speech segregation models. Despite their success and growing applicability, few
efforts have been made to analyze the underlying principles that these networks
learn to perform segregation. Here we analyze the role of harmonicity on two
state-of-the-art Deep Neural Networks (DNN)-based models- Conv-TasNet and
DPT-Net. We evaluate their performance with mixtures of natural speech versus
slightly manipulated inharmonic speech, where harmonics are slightly frequency
jittered. We find that performance deteriorates …

arxiv role segregation speech systems