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

I tiakina i:
Ngā taipitopito rārangi puna kōrero
I whakaputaina i:arXiv.org (Dec 13, 2024), p. n/a
Kaituhi matua: Sridhar, Arvind Krishna
Ētahi atu kaituhi: Guo, Yinyi, Visser, Erik
I whakaputaina:
Cornell University Library, arXiv.org
Ngā marau:
Urunga tuihono:Citation/Abstract
Full text outside of ProQuest
Ngā Tūtohu: Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
Whakaahuatanga
Whakarāpopotonga: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
Puna:Engineering Database