Learning from Annotation Uncertainty: Entropy-Aware Curriculum for Speech Emotion Recognition
Speech emotion recognition (SER) often relies on hard consensus labels that collapse annotator disagreement. We study distribution-based supervision for 9-class SER on MSP-Podcast 2.0 using a WavLM-Base multitask model for categorical emotion and dimensional VAD. Hard-label training is compared with targets from primary and merged primary--secondary annotator vote distributions. Distributional objectives improve alignment with human vote distributions, reducing JSD/KLD relative to hard-label training. Analysis shows that hard supervision partly benefits from assigning ambiguous utterances to the residual Other class, whereas distributional supervision redistributes uncertainty across emotion categories. Entropy-stratified evaluation shows that high-ambiguity utterances remain challenging, but distribution-based supervision better captures perceptual uncertainty. These findings support moving beyond hard labels toward targets that reflect listener disagreement.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech Emotion RecognitionSimilar Papers 제목 키워드 기반
Uncertainty-Aware Curriculum Learning for Neural Machine Translation
Neural machine translation (NMT) has proven to be facilitated by curriculum learning which presents examples in an easy-to-hard order at different training stages. The keys lie in the assessment of data difficulty and mo…
Machine TranslationNMTTranslationMap-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
We address the problem of semantic nighttime image segmentation and improve the state-of-the-art, by adapting daytime models to nighttime without using nighttime annotations. Moreover, we design a new evaluation framewor…
Domain AdaptationImage SegmentationSegmentationSemantic SegmentationGuided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
Most progress in semantic segmentation reports on daytime images taken under favorable illumination conditions. We instead address the problem of semantic segmentation of nighttime images and improve the state-of-the-art…
Image SegmentationSegmentationSemantic SegmentationStyle TransferPaced-Curriculum Distillation with Prediction and Label Uncertainty for Image Segmentation
Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While…
Image SegmentationMedical Image SegmentationScene SegmentationSegmentation+2Naturalness-Aware Curriculum Learning with Dynamic Temperature for Speech Deepfake Detection
Recent advances in speech deepfake detection (SDD) have significantly improved artifacts-based detection in spoofed speech. However, most models overlook speech naturalness, a crucial cue for distinguishing bona fide spe…
DeepFake DetectionFace Swapping