Resurfacing Paralinguistic Awareness in Large Audio Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Hao, Wang, Minghan, Wu, Tongtong, Qu, Lizhen, Shareghi, Ehsan, Haffari, Gholamreza
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915857445158912
author Yang, Hao
Wang, Minghan
Wu, Tongtong
Qu, Lizhen
Shareghi, Ehsan
Haffari, Gholamreza
author_facet Yang, Hao
Wang, Minghan
Wu, Tongtong
Qu, Lizhen
Shareghi, Ehsan
Haffari, Gholamreza
contents Large Audio Language Models (LALMs) have expanded the interaction with human to speech modality, which introduces great interactive potential, due to the paralinguistic cues implicitly indicating the user context. However, building on the current content-centred paradigm, LALMs usually neglect such paralinguistic cues and respond solely based on query content. In this work, to resurface the paralinguistic awareness in LALMs, we introduce five diverse layer-wise analyses to jointly identify paralinguistic layers and semantic understanding layers. Based on these insights, we propose a paralinguistic-enhanced fine-tuning (PE-FT) protocol accordingly to equip LALMs with paralinguistic-aware capabilities, including (1) selective-layer fine-tuning, and (2) an auxiliary dual-level classification head. Our experiments demonstrate that PE-FT protocol efficiently and effectively resurfaces the paralinguistic awareness, even surpassing the performance of the all-layer fine-tuning strategy.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11947
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Resurfacing Paralinguistic Awareness in Large Audio Language Models
Yang, Hao
Wang, Minghan
Wu, Tongtong
Qu, Lizhen
Shareghi, Ehsan
Haffari, Gholamreza
Sound
Computation and Language
Multimedia
Audio and Speech Processing
Large Audio Language Models (LALMs) have expanded the interaction with human to speech modality, which introduces great interactive potential, due to the paralinguistic cues implicitly indicating the user context. However, building on the current content-centred paradigm, LALMs usually neglect such paralinguistic cues and respond solely based on query content. In this work, to resurface the paralinguistic awareness in LALMs, we introduce five diverse layer-wise analyses to jointly identify paralinguistic layers and semantic understanding layers. Based on these insights, we propose a paralinguistic-enhanced fine-tuning (PE-FT) protocol accordingly to equip LALMs with paralinguistic-aware capabilities, including (1) selective-layer fine-tuning, and (2) an auxiliary dual-level classification head. Our experiments demonstrate that PE-FT protocol efficiently and effectively resurfaces the paralinguistic awareness, even surpassing the performance of the all-layer fine-tuning strategy.
title Resurfacing Paralinguistic Awareness in Large Audio Language Models
topic Sound
Computation and Language
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2603.11947