Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models

Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability. However, these models may amplify biases present in training da...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-07
Main Authors: Yi-Cheng, Lin, Lin, Tzu-Quan, Chih-Kai, Yang, Ke-Han, Lu, Chen, Wei-Chih, Chun-Yi, Kuan, Hung-yi, Lee
Format: Article
Language:English
Subjects:
Audio data
Emotion recognition
Human bias
Large language models
Semantics
Speech recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability. However, these models may amplify biases present in training data, potentially leading to biased access to information for marginalized groups. This work introduces a curated spoken bias evaluation toolkit and corresponding dataset. We evaluate gender bias in SILLMs across four semantic-related tasks: speech-to-text translation (STT), spoken coreference resolution (SCR), spoken sentence continuation (SSC), and spoken question answering (SQA). Our analysis reveals that bias levels are language-dependent and vary with different evaluation methods. Our findings emphasize the necessity of employing multiple approaches to comprehensively assess biases in SILLMs, providing insights for developing fairer SILLM systems.
ISSN:2331-8422