mlsanityData to 14 Oct 2026

Uncertainty Calibration for Deep Audio Classifiers

arXiv 2206.13071 ↗First posted 27 Jun 2022cs.SD cs.LG eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

Although deep Neural Networks (DNNs) have achieved tremendous success in audio classification tasks, their uncertainty calibration are still under-explored. A well-calibrated model should be accurate when it is certain about its prediction and indicate high uncertainty when it is likely to be inaccurate. In this work, we investigate the uncertainty calibration for deep audio classifiers. In particular, we empirically study the performance of popular calibration methods: (i) Monte Carlo Dropout, (ii) ensemble, (iii) focal loss, and (iv) spectral-normalized Gaussian process (SNGP), on audio classification datasets. To this end, we evaluate (i-iv) for the tasks of environment sound and music genre classification. Results indicate that uncalibrated deep audio classifiers may be over-confident, and SNGP performs the best and is very efficient on the two datasets of this paper.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 27 Jun 2022.

Builds on

25 of 37 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  7. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  9. 2019When Does Label Smoothing Help?cited by 988
  10. 2016CNN Architectures for Large-Scale Audio Classificationcited by 704
  11. 2017On Fairness and Calibrationcited by 406
  12. 2021Revisiting the Calibration of Modern Neural Networkscited by 390
13 more
  1. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  2. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 364
  3. 2020Calibrating Deep Neural Networks using Focal Losscited by 357
  4. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 305
  5. 2020Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learningcited by 190
  6. 2020Masksembles for Uncertainty Estimationcited by 88
  7. 2020Intra Order-preserving Functions for Calibration of Multi-Class Neural Networkscited by 65
  8. 2020Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binningcited by 27
  9. 2021On the Calibration and Uncertainty of Neural Learning to Rank Modelscited by 24
  10. 2020On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspectivecited by 21
  11. 2021Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Modelscited by 18
  12. 2022Towards Speaker Age Estimation with Label Distribution Learningcited by 13
  13. 2021Variational Information Bottleneck for Effective Low-resource Audio Classificationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Uncertainty Calibration of Multi-Label Bird Sound Classifierscited by 1
  2. 2026TCPα: Margin-Controlled Confidence estimation for reliable Music Information Retrievalcited by 0