Research map / Architectures and efficiency / RNNs and normalization
Learnable Fractional Superlets with a Spectro-Temporal Emotion Encoder for Speech Emotion Recognition
Alaa Nfissi, Wassim Bouachir, Nizar Bouguila, Brian L Mishara
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| make superlet orders, cycles and frequency grid learnable (LFST) instead of fixed superlet (ablation) | STEE · NSPL-CRISE | accuracy (%): 74.9 -> 76.9 | Improved |
| make superlet orders, cycles and frequency grid learnable (LFST) instead of fixed superlet (ablation) | STEE · IEMOCAP | accuracy (%): 86.0 -> 87.5 | Improved |
| make superlet orders, cycles and frequency grid learnable (LFST) instead of fixed superlet (ablation) | STEE · EMO-DB | accuracy (%): 90.1 -> 91.4 | Improved |
| use LFST front-end instead of STFT | STEE · NSPL-CRISE | accuracy (%): 73.1 -> 76.9 | Improved |
| use LFST front-end instead of LEAF | STEE · NSPL-CRISE | F1-score (%): 72.1 -> 76.6 | Improved |
| use LFST front-end instead of Morlet wavelet (c=3) (ablation) | STEE · IEMOCAP | F1-score (%): 84.8 -> 86.8 | Improved |
| use fixed Morlet wavelet instead of STFT | STEE · NSPL-CRISE | accuracy (%): 73.1 -> 74.6 | Improved |
| use LEAF instead of STFT | STEE · IEMOCAP | accuracy (%): 84.8 -> 84.9 | No clear effect |
| use fixed superlet instead of Morlet wavelet | STEE · EMO-DB | accuracy (%): 90.1 -> 90.1 | No clear effect |
| use LFST instead of STFT front-end | STEE · complexity (1 s input) | FLOPs (GF): 0.36 -> 201.5 | Hurt |
| use LFST instead of STFT front-end | STEE · complexity (1 s input) | latency (ms): 2.2 -> 74.9 | Hurt |
| use LFST instead of LEAF front-end | STEE · complexity (1 s input) | peak memory (MB): 1156.0 -> 4532.8 | Hurt |
Closest papers by meaning
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.82)
- Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning (NeurIPS 2024 · similarity 0.82)
- Multi-to-Single: Reducing Multimodal Dependency in Emotion Recognition Through Contrastive Learning (AAAI 2025 · similarity 0.82)
- OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition (ICML 2025 · similarity 0.82)
- Personalized Dynamic Music Emotion Recognition with Dual-Scale Attention-Based Meta-Learning (AAAI 2025 · similarity 0.81)
- DMMR: Cross-Subject Domain Generalization for EEG-Based Emotion Recognition via Denoising Mixed Mutual Reconstruction (AAAI 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
