Describe Where You Are: Improving Noise-Robustness for Speech Emotion Recognition with Text Description of the Environment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Leem, Seong-Gyun, Fulford, Daniel, Onnela, Jukka-Pekka, Gard, David, Busso, Carlos
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911254597074944
author Leem, Seong-Gyun
Fulford, Daniel
Onnela, Jukka-Pekka
Gard, David
Busso, Carlos
author_facet Leem, Seong-Gyun
Fulford, Daniel
Onnela, Jukka-Pekka
Gard, David
Busso, Carlos
contents Speech emotion recognition (SER) systems often struggle in real-world environments, where ambient noise severely degrades their performance. This paper explores a novel approach that exploits prior knowledge of testing environments to maximize SER performance under noisy conditions. To address this task, we propose a text-guided, environment-aware training where an SER model is trained with contaminated speech samples and their paired noise description. We use a pre-trained text encoder to extract the text-based environment embedding and then fuse it to a transformer-based SER model during training and inference. We demonstrate the effectiveness of our approach through our experiment with the MSP-Podcast corpus and real-world additive noise samples collected from the Freesound and DEMAND repositories. Our experiment indicates that the text-based environment descriptions processed by a large language model (LLM) produce representations that improve the noise-robustness of the SER system. With a contrastive learning (CL)-based representation, our proposed method can be improved by jointly fine-tuning the text encoder with the emotion recognition model. Under the -5dB signal-to-noise ratio (SNR) level, fine-tuning the text encoder improves our CL-based representation method by 76.4% (arousal), 100.0% (dominance), and 27.7% (valence).
format Preprint
id arxiv_https___arxiv_org_abs_2407_17716
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Describe Where You Are: Improving Noise-Robustness for Speech Emotion Recognition with Text Description of the Environment
Leem, Seong-Gyun
Fulford, Daniel
Onnela, Jukka-Pekka
Gard, David
Busso, Carlos
Sound
Computation and Language
Machine Learning
Audio and Speech Processing
Speech emotion recognition (SER) systems often struggle in real-world environments, where ambient noise severely degrades their performance. This paper explores a novel approach that exploits prior knowledge of testing environments to maximize SER performance under noisy conditions. To address this task, we propose a text-guided, environment-aware training where an SER model is trained with contaminated speech samples and their paired noise description. We use a pre-trained text encoder to extract the text-based environment embedding and then fuse it to a transformer-based SER model during training and inference. We demonstrate the effectiveness of our approach through our experiment with the MSP-Podcast corpus and real-world additive noise samples collected from the Freesound and DEMAND repositories. Our experiment indicates that the text-based environment descriptions processed by a large language model (LLM) produce representations that improve the noise-robustness of the SER system. With a contrastive learning (CL)-based representation, our proposed method can be improved by jointly fine-tuning the text encoder with the emotion recognition model. Under the -5dB signal-to-noise ratio (SNR) level, fine-tuning the text encoder improves our CL-based representation method by 76.4% (arousal), 100.0% (dominance), and 27.7% (valence).
title Describe Where You Are: Improving Noise-Robustness for Speech Emotion Recognition with Text Description of the Environment
topic Sound
Computation and Language
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2407.17716