animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics

• URL: http://arxiv.org/abs/2406.01253v1
• Date: Mon, 3 Jun 2024 12:11:01 GMT
• Title: animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics
• Authors: Julian C. Schäfer-Zimmermann, Vlad Demartsev, Baptiste Averly, Kiran Dhanjal-Adams, Mathieu Duteil, Gabriella Gall, Marius Faiß, Lily Johnson-Ulrich, Dan Stowell, Marta B. Manser, Marie A. Roch, Ariana Strandburg-Peshkin,
• Abstract summary: We present the animal2vec framework, a fully interpretable transformer model and self-supervised training scheme tailored for sparse and unbalanced bioacoustic data. We openly publish MeerKAT: Meerkat Kalahari Audio Transcripts, a large-scale dataset containing audio collected via biologgers on free-ranging meerkats with a length of over 1068h. We report new state-of-the-art results on both datasets and evaluate the few-shot capabilities of animal2vec of labeled training data.
• Score: 2.1019401515721583
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bioacoustic research provides invaluable insights into the behavior, ecology, and conservation of animals. Most bioacoustic datasets consist of long recordings where events of interest, such as vocalizations, are exceedingly rare. Analyzing these datasets poses a monumental challenge to researchers, where deep learning techniques have emerged as a standard method. Their adaptation remains challenging, focusing on models conceived for computer vision, where the audio waveforms are engineered into spectrographic representations for training and inference. We improve the current state of deep learning in bioacoustics in two ways: First, we present the animal2vec framework: a fully interpretable transformer model and self-supervised training scheme tailored for sparse and unbalanced bioacoustic data. Second, we openly publish MeerKAT: Meerkat Kalahari Audio Transcripts, a large-scale dataset containing audio collected via biologgers deployed on free-ranging meerkats with a length of over 1068h, of which 184h have twelve time-resolved vocalization-type classes, each with ms-resolution, making it the largest publicly-available labeled dataset on terrestrial mammals. Further, we benchmark animal2vec against the NIPS4Bplus birdsong dataset. We report new state-of-the-art results on both datasets and evaluate the few-shot capabilities of animal2vec of labeled training data. Finally, we perform ablation studies to highlight the differences between our architecture and a vanilla transformer baseline for human-produced sounds. animal2vec allows researchers to classify massive amounts of sparse bioacoustic data even with little ground truth information available. In addition, the MeerKAT dataset is the first large-scale, millisecond-resolution corpus for benchmarking bioacoustic models in the pretrain/finetune paradigm. We believe this sets the stage for a new reference point for bioacoustics.

Related papers

• The iNaturalist Sounds Dataset [60.157076990024606]
  iNatSounds is a collection of 230,000 audio files capturing sounds from over 5,500 species, contributed by more than 27,000 recordists worldwide.<n>The dataset encompasses sounds from birds, mammals, insects, reptiles, and amphibians, with audio and species labels derived from observations submitted to iNaturalist.<n>We envision models trained on this data powering next-generation public engagement applications, and assisting biologists, ecologists, and land use managers in processing large audio collections.
  arXiv  Detail & Related papers  (2025-05-31T02:07:37Z)
• Multi Modal Information Fusion of Acoustic and Linguistic Data for Decoding Dairy Cow Vocalizations in Animal Welfare Assessment [0.0]
  This study aims to decode dairy cow contact calls by employing multi-modal data fusion techniques. We utilize the Natural Language Processing model to transcribe audio recordings of cow vocalizations into written form. We categorized vocalizations into high frequency calls associated with distress or arousal, and low frequency calls linked to contentment or calmness.
  arXiv  Detail & Related papers  (2024-11-01T09:48:30Z)
• Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data [69.7174072745851]
  We present Synthio, a novel approach for augmenting small-scale audio classification datasets with synthetic data. To overcome the first challenge, we align the generations of the T2A model with the small-scale dataset using preference optimization. To address the second challenge, we propose a novel caption generation technique that leverages the reasoning capabilities of Large Language Models.
  arXiv  Detail & Related papers  (2024-10-02T22:05:36Z)
• WhaleNet: a Novel Deep Learning Architecture for Marine Mammals Vocalizations on Watkins Marine Mammal Sound Database [49.1574468325115]
  We introduce textbfWhaleNet (Wavelet Highly Adaptive Learning Ensemble Network), a sophisticated deep ensemble architecture for the classification of marine mammal vocalizations. We achieve an improvement in classification accuracy by $8-10%$ over existing architectures, corresponding to a classification accuracy of $97.61%$.
  arXiv  Detail & Related papers  (2024-02-20T11:36:23Z)
• OmniMotionGPT: Animal Motion Generation with Limited Data [70.35662376853163]
  We introduce AnimalML3D, the first text-animal motion dataset with 1240 animation sequences spanning 36 different animal identities. We are able to generate animal motions with high diversity and fidelity, quantitatively and qualitatively outperforming the results of training human motion generation baselines on animal data.
  arXiv  Detail & Related papers  (2023-11-30T07:14:00Z)
• Exploring Meta Information for Audio-based Zero-shot Bird Classification [113.17261694996051]
  This study investigates how meta-information can improve zero-shot audio classification. We use bird species as an example case study due to the availability of rich and diverse meta-data.
  arXiv  Detail & Related papers  (2023-09-15T13:50:16Z)
• Transferable Models for Bioacoustics with Human Language Supervision [0.0]
  BioLingual is a new model for bioacoustics based on contrastive language-audio pretraining. It can identify over a thousand species' calls across taxa, complete bioacoustic tasks zero-shot, and retrieve animal vocalization recordings from natural text queries.
  arXiv  Detail & Related papers  (2023-08-09T14:22:18Z)
• Classification of animal sounds in a hyperdiverse rainforest using Convolutional Neural Networks [0.0]
  Automated species detection from passively recorded soundscapes via machine-learning approaches is a promising technique. We use soundscapes from a tropical forest in Borneo and a Convolutional Neural Network model (CNN) created with transfer learning. Our results suggest that transfer learning and data augmentation can make the use of CNNs to classify species' vocalizations feasible even for small soundscape-based projects with many rare species.
  arXiv  Detail & Related papers  (2021-11-29T21:34:57Z)
• Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales [97.41394631426678]
  Recent research showed the promise of machine learning tools for analyzing acoustic communication in nonhuman species. We outline the key elements required for the collection and processing of massive bioacoustic data of sperm whales. The technological capabilities developed are likely to yield cross-applications and advancements in broader communities investigating non-human communication and animal behavioral research.
  arXiv  Detail & Related papers  (2021-04-17T18:39:22Z)
• AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild [51.35013619649463]
  We present an extensive dataset of free-running cheetahs in the wild, called AcinoSet. The dataset contains 119,490 frames of multi-view synchronized high-speed video footage, camera calibration files and 7,588 human-annotated frames. The resulting 3D trajectories, human-checked 3D ground truth, and an interactive tool to inspect the data is also provided.
  arXiv  Detail & Related papers  (2021-03-24T15:54:11Z)
• Modelling Animal Biodiversity Using Acoustic Monitoring and Deep Learning [0.0]
  This paper outlines an approach for achieving this using state of the art in machine learning to automatically extract features from time-series audio signals. The acquired bird songs are processed using mel-frequency cepstrum (MFC) to extract features which are later classified using a multilayer perceptron (MLP) Our proposed method achieved promising results with 0.74 sensitivity, 0.92 specificity and an accuracy of 0.74.
  arXiv  Detail & Related papers  (2021-03-12T13:50:31Z)

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.