Visual Transformers for Primates Classification and Covid Detection

Illium, Steffen; Müller, Robert; Sedlmeier, Andreas; Popien, Claudia-Linnhoff

doi:10.21437/interspeech.2021-273

Cited by 10 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANIMAL-SPOT demonstrated also great results in terms of single-stage multi-species primate classification, by outperforming the ComParE baseline system. The final result of 89.3% also exceeds the UAR of 88.3% presented by challenge competitor Illium et al 50 , who applied a vision transformer to the classification problem. Müller et al 51 report the same UAR of 89.3% while applying a Deep Recurrent Neural Network.…”

Section: Discussion and Future Outlookmentioning

confidence: 67%

ANIMAL-SPOT enables animal-independent signal detection and classification using deep learning

Bergler

Smeele

Tyndel

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Bioacoustic research spans a wide range of biological questions and applications, relying on identification of target species or smaller acoustic units, such as distinct call types. However, manually identifying the signal of interest is time-intensive, error-prone, and becomes unfeasible with large data volumes. Therefore, machine-driven algorithms are increasingly applied to various bioacoustic signal identification challenges. Nevertheless, biologists still have major difficulties trying to transfer existing animal- and/or scenario-related machine learning approaches to their specific animal datasets and scientific questions. This study presents an animal-independent, open-source deep learning framework, along with a detailed user guide. Three signal identification tasks, commonly encountered in bioacoustics research, were investigated: (1) target signal vs. background noise detection, (2) species classification, and (3) call type categorization. ANIMAL-SPOT successfully segmented human-annotated target signals in data volumes representing 10 distinct animal species and 1 additional genus, resulting in a mean test accuracy of 97.9%, together with an average area under the ROC curve (AUC) of 95.9%, when predicting on unseen recordings. Moreover, an average segmentation accuracy and F1-score of 95.4% was achieved on the publicly available BirdVox-Full-Night data corpus. In addition, multi-class species and call type classification resulted in 96.6% and 92.7% accuracy on unseen test data, as well as 95.2% and 88.4% regarding previous animal-specific machine-based detection excerpts. Furthermore, an Unweighted Average Recall (UAR) of 89.3% outperformed the multi-species classification baseline system of the ComParE 2021 Primate Sub-Challenge. Besides animal independence, ANIMAL-SPOT does not rely on expert knowledge or special computing resources, thereby making deep-learning-based bioacoustic signal identification accessible to a broad audience.

show abstract

Section: Discussion and Future Outlookmentioning

confidence: 67%

ANIMAL-SPOT enables animal-independent signal detection and classification using deep learning

Bergler

Smeele

Tyndel

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…UAR is equivalent to balanced accuracy. We note that if F1 had been the evaluation metric, Illium, et al ( 25 ) would have infact won the cough sub challenge. This is thanks to their model’s superior precision performance, i.e., what proportion of the model’s positive predictions are correct.…”

mentioning

confidence: 78%

“…Team Casanova et al exploited a noise addition method and SpecAugment to augment the challenge dataset ( 23 ). Team Illium et al targeted spectrogram-level augmentations with temporal shifting, noise addition, SpecAugment and loudness adjustment ( 25 ). Instead of using a data augmentation method to manipulate the challenge dataset, team Klumpp et al used three auxiliary datasets in different languages aiming their deep acoustic model to better learn the properties of healthy speech ( 24 ).…”

Section: Overview Of Methodologies Used In Accepted Papers At Intersp...mentioning

confidence: 99%

“…They explored the complexity parameter of the SVM ranging from

1

. Team Illium et al ( 25 ) adapted a vision transformer ( 38 ) for mel-spectrogram representations of audio signals. Tree-structured Parzen Estimator-algorithm (TPE) ( 39 ) was exploited in ( 25 ) for hyperparameter search mainly exploring embedding size, learning rate, batch size, dropout, number of heads and head dimension.…”

Section: Overview Of Methodologies Used In Accepted Papers At Intersp...mentioning

confidence: 99%

“…Team Illium et al ( 25 ) adapted a vision transformer ( 38 ) for mel-spectrogram representations of audio signals. Tree-structured Parzen Estimator-algorithm (TPE) ( 39 ) was exploited in ( 25 ) for hyperparameter search mainly exploring embedding size, learning rate, batch size, dropout, number of heads and head dimension. The teams Solera-Urena et al, Casanova et al, and the baseline also reported classification results by using the fusion of their best features and classifiers.…”

Section: Overview Of Methodologies Used In Accepted Papers At Intersp...mentioning

confidence: 99%

See 2 more Smart Citations

A summary of the ComParE COVID-19 challenges

Coppock

Akman²,

Bergler³

et al. 2023

Front. Digit. Health

View full text Add to dashboard Cite

The COVID-19 pandemic has caused massive humanitarian and economic damage. Teams of scientists from a broad range of disciplines have searched for methods to help governments and communities combat the disease. One avenue from the machine learning field which has been explored is the prospect of a digital mass test which can detect COVID-19 from infected individuals’ respiratory sounds. We present a summary of the results from the INTERSPEECH 2021 Computational Paralinguistics Challenges: COVID-19 Cough, (CCS) and COVID-19 Speech, (CSS).

show abstract