Saved in:
Bibliographic Details
Main Authors: Shome, Debaditya, Etemad, Ali
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.04849
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909137446633472
author Shome, Debaditya
Etemad, Ali
author_facet Shome, Debaditya
Etemad, Ali
contents We propose EmoDistill, a novel speech emotion recognition (SER) framework that leverages cross-modal knowledge distillation during training to learn strong linguistic and prosodic representations of emotion from speech. During inference, our method only uses a stream of speech signals to perform unimodal SER thus reducing computation overhead and avoiding run-time transcription and prosodic feature extraction errors. During training, our method distills information at both embedding and logit levels from a pair of pre-trained Prosodic and Linguistic teachers that are fine-tuned for SER. Experiments on the IEMOCAP benchmark demonstrate that our method outperforms other unimodal and multimodal techniques by a considerable margin, and achieves state-of-the-art performance of 77.49% unweighted accuracy and 78.91% weighted accuracy. Detailed ablation studies demonstrate the impact of each component of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2309_04849
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations
Shome, Debaditya
Etemad, Ali
Computation and Language
Artificial Intelligence
Machine Learning
We propose EmoDistill, a novel speech emotion recognition (SER) framework that leverages cross-modal knowledge distillation during training to learn strong linguistic and prosodic representations of emotion from speech. During inference, our method only uses a stream of speech signals to perform unimodal SER thus reducing computation overhead and avoiding run-time transcription and prosodic feature extraction errors. During training, our method distills information at both embedding and logit levels from a pair of pre-trained Prosodic and Linguistic teachers that are fine-tuned for SER. Experiments on the IEMOCAP benchmark demonstrate that our method outperforms other unimodal and multimodal techniques by a considerable margin, and achieves state-of-the-art performance of 77.49% unweighted accuracy and 78.91% weighted accuracy. Detailed ablation studies demonstrate the impact of each component of our method.
title Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2309.04849