The research archive
Publications.
Papers, methods, and the questions they open.
Records / 11
- 2026
International Conference on Learning Representations (ICLR)
Learnable Fractional Superlets with a Spectro-Temporal Emotion Encoder for Speech Emotion Recognition
Learning fractional superlet representations alongside a spectro-temporal encoder for speech emotion recognition.
- 2025
Applied Intelligence
From unaltered raw waveform to emotion: Synergizing convolutional and gated recurrent networks for holistic speech emotion analysis
A journal study of CNN-n-GRU on TESS, IEMOCAP and RAVDESS, with generalization to spontaneous speech left open.
- 2025
Canadian Conference on Artificial Intelligence (Canadian AI)
Multimodal Emotion Recognition with Cross-Attentive Learning and Feature Fusion
Cross-attention fuses audio, text and video features for multimodal emotion recognition.
- 2025
Canadian Conference on Artificial Intelligence (Canadian AI)
Neural Wavelet Packet-Based Bidirectional Autoencoder for Multi-Resolution Speech Enhancement
A bidirectional autoencoder learns wavelet-packet representations for multiresolution speech enhancement.
- 2025
IEEE Transactions on Affective Computing
SigWavNet: Learning Multiresolution Signal Wavelet Network for Speech Emotion Recognition
A trainable multiresolution wavelet network combines raw-speech representations with spatial and temporal attention.
- 2024
International Conference on Machine Learning and Applications (ICMLA)
Learnable Deep Wavelet Packet Transform for Speech Emotion Recognition in High-Risk Suicide Calls
Learned wavelet-packet decomposition and denoising for speech emotion recognition on NSPL-CRISE and IEMOCAP.
- 2024
Artificial Neural Networks in Pattern Recognition (ANNPR 2024)
Deep Multiresolution Wavelet Transform for Speech Emotion Assessment of High-Risk Suicide Callers
Learnable wavelet analysis, spatial attention and temporal attention are combined for emotion assessment in helpline speech.
- 2024
Applied Intelligence
Unveiling hidden factors: explainable AI for feature boosting in speech emotion recognition
Iterative feature selection connects model explainability with evaluation across four speech-emotion benchmarks.
- 2024
2024 IEEE 18th International Conference on Semantic Computing (ICSC)
Unlocking the Emotional States of High-Risk Suicide Callers through Speech Analysis
A CNN–GRU speech-emotion study evaluated on NSPL-CRISE crisis-helpline recordings; ICSC 2024 best student paper.
- 2023
2023 22nd IEEE International Conference on Machine Learning and Applications (ICMLA)
Iterative Feature Boosting for Explainable Speech Emotion Recognition
A Shapley-guided loop refines acoustic feature sets for explainable speech emotion recognition.
- 2022
2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)
CNN-n-GRU: end-to-end speech emotion recognition from raw waveform signal using CNNs and gated recurrent unit networks
An end-to-end CNN–GRU model learns acoustic and temporal representations directly from speech waveforms.