Distilled Hubert For Mobile Speech Emotion Recognition: A Cross-corpus Validation Study

Abstract

Speech Emotion Recognition (SER) has significant potential for mobile applications, yet deployment remains constrained by the computational demands of state-of-the-art transformer architectures. This paper presents a mobile-efficient SER system based on DistilHuBERT, a distilled and 8-bit quantized transformer that achieves approximately 92% parameter reduction compared to full-scale Wav2Vec 2.0 models while maintaining competitive accuracy. We conduct a rigorous 5-fold Leave-One-Session-Out (LOSO) cross-validation on the IEMOCAP dataset to ensure speaker independence, augmented with cross-corpus training on CREMA-D to enhance generalization. Cross-corpus training with CREMA-D yields a 1.2% improvement in Weighted Accuracy, a 1.4% gain in Macro F1-score, and a 32% reduction in cross-fold variance, with the Neutral class showing the most substantial benefit at 5.4% F1-score improvement. Our approach achieves an Unweighted Accuracy of 61.4% with a quantized model footprint of only 23 MB,

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyismail2025distilled

Related papers

• Leveraging Cross-attention Transformer And Multi-feature Fusion For Cross-linguistic Speech Emotion Recognition (2025)4.52
• Dawn Of The Transformer Era In Speech Emotion Recognition: Closing The Valence Gap (2022)18.59
• Wav2small: Distilling Wav2vec2 To 72K Parameters For Low-resource Speech Emotion Recognition (2024)0.00
• Speech Emotion Recognition With Distilled Prosodic And Linguistic Affect Representations (2023)5.24
• Decoding Emotions: A Comprehensive Multilingual Study Of Speech Models For Speech Emotion Recognition (2023)0.00
• Towards Interpretable And Transferable Speech Emotion Recognition: Latent Representation Based Analysis Of Features, Methods And Corpora (2021)0.00
• Multi-microphone Speech Emotion Recognition Using The Hierarchical Token-semantic Audio Transformer Architecture (2024)5.24
• Speaker Emotion Recognition: Leveraging Self-supervised Models For Feature Extraction Using Wav2vec2 And Hubert (2024)0.00