ExHuBERT: Enhancing HuBERT Through Block Extension and Fine-Tuning on 37 Emotion Datasets
Abstract
Foundation models have shown great promise in speech emotion recognition (SER) by leveraging their pre-trained representations to capture emotion patterns in speech signals. To further enhance SER performance across various languages and domains, we propose a novel twofold approach. First, we gather EmoSet++, a comprehensive multi-lingual, multi-cultural speech emotion corpus with 37 datasets, 150,907 samples, and a total duration of 119.5 hours. Second, we introduce ExHuBERT, an enhanced version of HuBERT achieved by backbone extension and fine-tuning on EmoSet++. We duplicate each encoder layer and its weights, then freeze the first duplicate, integrating an extra zero-initialized linear layer and skip connections to preserve functionality and ensure its adaptability for subsequent fine-tuning. Our evaluation on unseen datasets shows the efficacy of ExHuBERT, setting a new benchmark for various SER tasks. Model and details on EmoSet++: https://huggingface.co/amiriparian/ExHuBERT.
- Publication:
-
arXiv e-prints
- Pub Date:
- June 2024
- DOI:
- 10.48550/arXiv.2406.10275
- arXiv:
- arXiv:2406.10275
- Bibcode:
- 2024arXiv240610275A
- Keywords:
-
- Computer Science - Computation and Language;
- 68T10;
- I.2
- E-Print:
- accepted at INTERSPEECH 2024