ExHuBERT: Enhancing HuBERT Through Block Extension and Fine-Tuning on 37 Emotion Datasets

MCML Authors

Shahin Amiriparian

Dr.

* Former Member

→ Group Björn Schuller
 Health Informatics

Filip Packań

→ Group Björn Schuller
 Health Informatics

Maurice Gerczuk

* Former Member

→ Group Björn Schuller
 Health Informatics

Björn Schuller

Prof. Dr.

Core PI

Health Informatics

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.

inproceedings APG+24

---

Interspeech 2024

25th Annual Conference of the International Speech Communication Association. Kos Island, Greece, Sep 01-05, 2024.

---

Authors

S. Amiriparian • F. Packań • M. Gerczuk • B. W. Schuller

---

Links

DOI

---

Research Area

 B3 | Multimodal Perception