Зображення обкладинки

Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models

Збережено в:
Опубліковано в::arXiv.org (Dec 13, 2024), p. n/a
Автор: Sridhar, Arvind Krishna
Інші автори: Guo, Yinyi, Visser, Erik
Опубліковано:
Cornell University Library, arXiv.org
Предмети:
Language
Questions
Data augmentation
Audio data
Large language models
Temporal logic
Reasoning
Онлайн доступ:Citation/Abstract
Full text outside of ProQuest
Теги: Додати тег
Немає тегів, Будьте першим, хто поставить тег для цього запису!
Короткий огляд:The Audio Question Answering (AQA) task includes audio event classification, audio captioning, and open-ended reasoning. Recently, AQA has garnered attention due to the advent of Large Audio Language Models (LALMs). Current literature focuses on constructing LALMs by integrating audio encoders with text-only Large Language Models (LLMs) through a projection module. While LALMs excel in general audio understanding, they are limited in temporal reasoning, which may hinder their commercial applications and on-device deployment. This paper addresses these challenges and limitations in audio temporal reasoning. First, we introduce a data augmentation technique for generating reliable audio temporal questions and answers using an LLM. Second, we perform a further fine-tuning of an existing baseline using curriculum learning strategy to specialize in temporal reasoning without compromising performance on fine-tuned tasks. We demonstrate the performance of our model using state-of-the-art LALMs on public audio benchmark datasets. Third, we implement our AQA model on-device locally and investigate its CPU inference for edge applications.
ISSN:2331-8422
Джерело:Engineering Database