MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training

• URL: http://arxiv.org/abs/2609.15221v1
• Date: Mon, 14 Sep 2026 08:41:23 GMT
• Title: MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training
• Abstract summary: Time-frequency annotation of animal vocalizations is expensive, site-specific, and difficult to sustain at scale.<n>We present a label-efficient sound detection framework that combines masked audio pretraining with a lightweight detector on mel spectrograms.<n>We evaluate the performance on two ecologically distinct domains: tropical rainforest soundscapes (Indonesia) and bird vocalizations in Mediterranean habitats (Spain)
• Score: 7.983925207958734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Passive acoustic monitoring can measure biodiversity at larger scales, but time--frequency annotation of animal vocalizations is expensive, site-specific, and difficult to sustain at scale. We present a label-efficient sound detection framework that combines masked audio pretraining with a lightweight detector on mel spectrograms, then further improves robustness through iterative self-training on unlabeled audio. We first pretrain a ViT-based encoder on unlabeled recordings via masked reconstruction and transfer the encoder to a detection backbone. To better separate animal sounds from confounding background, we add a box-level contrastive loss that pulls matched event regions together while pushing noisy negatives apart. We then apply a two-stage pseudo-labeling curriculum to exploit large unlabeled pools without additional annotation. We evaluate the performance on two ecologically distinct domains: tropical rainforest soundscapes (Indonesia) and bird vocalizations in Mediterranean habitats (Spain). On both domains, masked audio pretraining and contrastive learning consistently improve time--frequency detection under temporal and cross-site distribution shift, and self-training yields further gains in out-of-distribution performance. On the rainforest domain, MAST with self-training achieves +0.22 mAP and +0.24 F1 over the strongest baseline under cross-site shift. On the bird domain, self-training achieves +0.12 mAP and +0.10 F1 over the strongest baseline under cross-site shift. Overall, our results show that MAST can effectively extend self-supervised audio representations from clip-level tasks to robust box-level localization across diverse bioacoustic settings, providing a practical path for biodiversity monitoring with limited labels.

Related papers

• Uncertainty-Aware Crossmodal Fusion for Classification of Animal Behavior [1.6178468864923607]
  We propose Uncertainty-Aware Fusion (UAF), a dual-stream framework that estimates Gaussian uncertainty for each representation and fuses them via uncertainty weighting.<n>UAF achieves 59.4% accuracy / 39.7% macro F1 on the 17-class SoundWel pig vocalization benchmark and 73.1% accuracy / 71.5% macro F1 on the 3-class DogBark dataset, outperforming static-concatenation fusion by 15.7% and 20.4% relative macro F1, respectively.
  arXiv  Detail & Related papers  (2026-08-03T12:05:28Z)
• Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study [20.469464200788583]
  Masked autoencoders (MAE) have shown strong transferability on massive audio corpora.<n>We conduct a systematic study of MAE pretraining for species classification on iNatSounds.<n>Our results indicate that, in moderate-sized fine-grained bioacoustic settings, pretraining scale dominates objective design.
  arXiv  Detail & Related papers  (2026-05-13T18:45:08Z)
• Semi-supervised classification of bird vocalizations [0.0]
  Changes in bird populations can indicate broader changes in ecosystems.<n>We propose a semi-supervised acoustic bird detector to allow the detection of time-overlapping calls.<n>It achieves a mean F0.5 score of 0.701 across 315 classes from 110 bird species on a hold-out test set.
  arXiv  Detail & Related papers  (2025-02-19T05:31:13Z)
• animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics [2.1019401515721583]
  animal2vec is an interpretable large transformer model that learns from unlabeled audio and refines its understanding with labeled data. Meerkat Audio Transcripts is the largest labeled dataset on non-human terrestrial mammals. Our model outperforms existing methods on MeerKAT and the publicly available NIPS4Bplus birdsong dataset.
  arXiv  Detail & Related papers  (2024-06-03T12:11:01Z)
• Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacoustics [5.799126142155481]
  Machine learning has the potential to revolutionize passive acoustic monitoring (PAM) for ecological assessments. Generalizable pretrained networks can overcome these costs, but high-quality pretraining requires vast annotated libraries. Here, we identify the optimum pretraining strategy for a data-deficient domain using coral reef bioacoustics.
  arXiv  Detail & Related papers  (2024-04-25T09:12:35Z)
• All Thresholds Barred: Direct Estimation of Call Density in Bioacoustic Data [1.7916003204531015]
  We propose a validation scheme for estimating call density in a body of data. We use these distributions to predict site-level densities, which may be subject to distribution shifts.
  arXiv  Detail & Related papers  (2024-02-23T14:52:44Z)
• A denoised Mean Teacher for domain adaptive point cloud registration [81.43344461130474]
  Point cloud-based medical registration promises increased computational efficiency, robustness to intensity shifts, and anonymity preservation. Supervised training on synthetic deformations is an alternative but, in turn, suffers from the domain gap to the real domain. We present a denoised teacher-student paradigm for point cloud registration, comprising two complementary denoising strategies.
  arXiv  Detail & Related papers  (2023-06-26T15:03:47Z)
• PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels [49.43183579415899]
  Convolutional Neural Networks (CNNs) have demonstrated superiority in learning patterns, but are sensitive to label noises and may overfit noisy labels during training. The early stopping strategy averts updating CNNs during the early training phase and is widely employed in the presence of noisy labels. Our proposed Phase-AmplituDe DisentangLed Early Stopping (PADDLES) method is shown to be effective on both synthetic and real-world label-noise datasets.
  arXiv  Detail & Related papers  (2022-12-07T05:03:13Z)
• AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach [50.855679274530615]
  We present a novel domain-adaptive approach called AdaStereo to align multi-level representations for deep stereo matching networks. Our models achieve state-of-the-art cross-domain performance on multiple benchmarks, including KITTI, Middlebury, ETH3D and DrivingStereo. Our method is robust to various domain adaptation settings, and can be easily integrated into quick adaptation application scenarios and real-world deployments.
  arXiv  Detail & Related papers  (2021-12-09T15:10:47Z)
• S3: Supervised Self-supervised Learning under Label Noise [53.02249460567745]
  In this paper we address the problem of classification in the presence of label noise. In the heart of our method is a sample selection mechanism that relies on the consistency between the annotated label of a sample and the distribution of the labels in its neighborhood in the feature space. Our method significantly surpasses previous methods on both CIFARCIFAR100 with artificial noise and real-world noisy datasets such as WebVision and ANIMAL-10N.
  arXiv  Detail & Related papers  (2021-11-22T15:49:20Z)
• Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification [61.54074498090374]
  This study introduces a CRSS-Forensics audio dataset collected in multiple acoustic environments. We pre-train a CNN-based network using the VoxCeleb data, followed by an approach which fine-tunes part of the high-level network layers with clean speech from CRSS-Forensics.
  arXiv  Detail & Related papers  (2020-09-05T02:54:33Z)
• Unsupervised Domain Adaptation for Acoustic Scene Classification Using Band-Wise Statistics Matching [69.24460241328521]
  Machine learning algorithms can be negatively affected by mismatches between training (source) and test (target) data distributions. We propose an unsupervised domain adaptation method that consists of aligning the first- and second-order sample statistics of each frequency band of target-domain acoustic scenes to the ones of the source-domain training dataset. We show that the proposed method outperforms the state-of-the-art unsupervised methods found in the literature in terms of both source- and target-domain classification accuracy.
  arXiv  Detail & Related papers  (2020-04-30T23:56:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.