SeQuiFi: Mitigating Catastrophic Forgetting in Speech Emotion Recognition with Sequential Class-Finetuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jain, Sarthak, Phukan, Orchid Chetia, Behera, Swarup Ranjan, Buduru, Arun Balaji, Sharma, Rajesh
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929546650976256
author Jain, Sarthak
Phukan, Orchid Chetia
Behera, Swarup Ranjan
Buduru, Arun Balaji
Sharma, Rajesh
author_facet Jain, Sarthak
Phukan, Orchid Chetia
Behera, Swarup Ranjan
Buduru, Arun Balaji
Sharma, Rajesh
contents In this work, we introduce SeQuiFi, a novel approach for mitigating catastrophic forgetting (CF) in speech emotion recognition (SER). SeQuiFi adopts a sequential class-finetuning strategy, where the model is fine-tuned incrementally on one emotion class at a time, preserving and enhancing retention for each class. While various state-of-the-art (SOTA) methods, such as regularization-based, memory-based, and weight-averaging techniques, have been proposed to address CF, it still remains a challenge, particularly with diverse and multilingual datasets. Through extensive experiments, we demonstrate that SeQuiFi significantly outperforms both vanilla fine-tuning and SOTA continual learning techniques in terms of accuracy and F1 scores on multiple benchmark SER datasets, including CREMA-D, RAVDESS, Emo-DB, MESD, and SHEMO, covering different languages.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12567
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SeQuiFi: Mitigating Catastrophic Forgetting in Speech Emotion Recognition with Sequential Class-Finetuning
Jain, Sarthak
Phukan, Orchid Chetia
Behera, Swarup Ranjan
Buduru, Arun Balaji
Sharma, Rajesh
Audio and Speech Processing
Sound
68T45
I.2.7
In this work, we introduce SeQuiFi, a novel approach for mitigating catastrophic forgetting (CF) in speech emotion recognition (SER). SeQuiFi adopts a sequential class-finetuning strategy, where the model is fine-tuned incrementally on one emotion class at a time, preserving and enhancing retention for each class. While various state-of-the-art (SOTA) methods, such as regularization-based, memory-based, and weight-averaging techniques, have been proposed to address CF, it still remains a challenge, particularly with diverse and multilingual datasets. Through extensive experiments, we demonstrate that SeQuiFi significantly outperforms both vanilla fine-tuning and SOTA continual learning techniques in terms of accuracy and F1 scores on multiple benchmark SER datasets, including CREMA-D, RAVDESS, Emo-DB, MESD, and SHEMO, covering different languages.
title SeQuiFi: Mitigating Catastrophic Forgetting in Speech Emotion Recognition with Sequential Class-Finetuning
topic Audio and Speech Processing
Sound
68T45
I.2.7
url https://arxiv.org/abs/2410.12567