ABSTRACT
We introduce the Bioacoustic Cocktail Party Problem Network (BioCPPNet), a lightweight, modular, and robust U-Net-based machine learning architecture optimized for bioacoustic source separation across diverse biological taxa. Employing learnable or handcrafted encoders, BioCPPNet operates directly on the raw acoustic mixture waveform containing overlapping vocalizations and separates the input waveform into estimates corresponding to the sources in the mixture. Predictions are compared to the reference ground truth waveforms by searching over the space of (output, target) source order permutations, and we train using an objective function motivated by perceptual audio quality. We apply BioCPPNet to several species with unique vocal behavior, including macaques, bottlenose dolphins, and Egyptian fruit bats, and we evaluate reconstruction quality of separated waveforms using the scale-invariant signal-to-distortion ratio (SI-SDR) and downstream identity classification accuracy. We consider mixtures with two or three concurrent conspecific vocalizers, and we examine separation performance in open and closed speaker scenarios. To our knowledge, this paper redefines the state-of-the-art in end-to-end single-channel bioacoustic source separation in a permutation-invariant regime across a heterogeneous set of non-human species. This study serves as a major step toward the deployment of bioacoustic source separation systems for processing substantial volumes of previously unusable data containing overlapping bioacoustic signals.
Subject(s)
Neural Networks, Computer , Vocalization, Animal/physiology , Acoustics , Animals , Humans , Machine LearningABSTRACT
An amendment to this paper has been published and can be accessed via a link at the top of the paper.
ABSTRACT
We implemented Machine Learning (ML) techniques to advance the study of sperm whale (Physeter macrocephalus) bioacoustics. This entailed employing Convolutional Neural Networks (CNNs) to construct an echolocation click detector designed to classify spectrograms generated from sperm whale acoustic data according to the presence or absence of a click. The click detector achieved 99.5% accuracy in classifying 650 spectrograms. The successful application of CNNs to clicks reveals the potential of future studies to train CNN-based architectures to extract finer-scale details from cetacean spectrograms. Long short-term memory and gated recurrent unit recurrent neural networks were trained to perform classification tasks, including (1) "coda type classification" where we obtained 97.5% accuracy in categorizing 23 coda types from a Dominica dataset containing 8,719 codas and 93.6% accuracy in categorizing 43 coda types from an Eastern Tropical Pacific (ETP) dataset with 16,995 codas; (2) "vocal clan classification" where we obtained 95.3% accuracy for two clan classes from Dominica and 93.1% for four ETP clan types; and (3) "individual whale identification" where we obtained 99.4% accuracy using two Dominica sperm whales. These results demonstrate the feasibility of applying ML to sperm whale bioacoustics and establish the validity of constructing neural networks to learn meaningful representations of whale vocalizations.
Subject(s)
Acoustics , Deep Learning , Signal Processing, Computer-Assisted , Sperm Whale , Animals , Echolocation , Sperm Whale/physiologyABSTRACT
Environmental enrichment (EE) replicates mind-body therapy by providing complex housing to laboratory animals to improve their activity levels, behavior, and social interactions. Using a Tcf4Het/+ApcMin/+-mediated model of colon tumorigenesis, we found that EE vastly improved the survival of tumor-bearing animals, with differential effect on tumor load in male compared to female animals. Analysis of Tcf4Het/+ApcMin/+ males showed drastically reduced expression of circulating inflammatory cytokines and induced nuclear hormone receptor (NHR) signaling, both of which are common in the wound repair process. Interestingly, EE provoked tumor wound repair resolution through revascularization, plasma cell recruitment and IgA secretion, replacement of glandular tumor structures with pericytes in a process reminiscent of scarring, and normalization of microbiota. These EE-dependent changes likely underlie the profound improvement in survival of colon-tumor-bearing Tcf4Het/+ApcMin/+ males. Our studies highlight the exciting promise of EE in the design of future therapeutic strategies for colon cancer patients.