Related papers: X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment

X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment

URL: http://arxiv.org/abs/2607.21550v1
Date: Thu, 23 Jul 2026 17:35:20 GMT
Title: X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment
Abstract summary: X$3$-OPD is a cross-modal on-policy distillation framework for large audio-language models.<n>It transfers reasoning capabilities from a powerful text teacher to an audio-language student.<n>X$3$-OPD substantially improves audio-grounded reasoning and chain-of-thought quality.
Score: 38.53954341285787
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
Abstract: While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in deep logical reasoning, primarily due to the scarcity of high-quality audio reasoning data. To bridge this gap, we propose X$^3$-OPD, a cross-modal on-policy distillation framework that transfers reasoning capabilities from a powerful text teacher to an audio-language student. During training, the student generates reasoning trajectories conditioned on its own acoustic perception, while the teacher provides token-level guidance using matched textual inputs and verified answers. We further construct a three-tier symmetric corpus covering textual reasoning rendered into speech, audio-event reasoning grounded in complex acoustic scenes, and spoken-dialogue reasoning involving paralinguistic cues. This design extends cross-modal distillation beyond textually recoverable content to reasoning grounded in non-linguistic events, prosody, and conversational context. Experiments on MMSU, MMAU, BIG Bench Audio, and MMAR demonstrate that X$^3$-OPD substantially improves audio-grounded reasoning and chain-of-thought quality while largely preserving the model's existing capabilities under domain shift.

Related papers

Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents [3.6734440150955368]
Audio language models (ALMs) are increasingly used for speech-based understanding.<n>The effects of accent variation, domain shift, and semantic over-inference on audio reasoning are poorly understood.<n>We evaluate audio language models across five semantic and paralinguistic reasoning tasks.
arXiv Detail & Related papers (2026-05-11T20:27:40Z)
Koopman Regularized Deep Speech Disentanglement for Speaker Verification [6.659299099827954]
Deep Koopman Speech Disentanglement Autoencoder (DKSD-AE)<n>We propose a structured autoencoder that combines a novel multi-step Koopman operator learning module with instance normalization to disentangle speaker and content dynamics.<n>Our findings suggest that Koopman-based temporal modelling, when combined with instance normalization, provides an efficient and principled solution for speaker-focused representation learning.
arXiv Detail & Related papers (2026-03-05T17:30:18Z)
Step-Audio-R1 Technical Report [70.37077572409319]
We introduce Step-Audio-R1, the first audio reasoning model that successfully unlocks reasoning capabilities in the audio domain.<n>Our model exhibits strong audio reasoning capabilities, surpassing Gemini 2.5 Pro and achieving performance comparable to the state-of-the-art Gemini 3 Pro.
arXiv Detail & Related papers (2025-11-19T20:12:50Z)
Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillation [52.537908557508324]
We propose a unified knowledge distillation framework to transfer reasoning capabilities from a high-capacity textual model to a student audio model.<n>Our method introduces two key dimensions: source-wise distillation and layer-wise distillation.<n> Experimental results show significant improvements in audio reasoning performance.
arXiv Detail & Related papers (2025-09-23T02:58:16Z)
Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models [80.75260664100644]
Mini-Omni-Reasoner is a framework that enables reasoning within speech via a novel "Thinking-in-Speaking" formulation.<n>It interleaves silent reasoning tokens with spoken response tokens at the token level.<n>It achieves a +19.1% gain in arithmetic reasoning and +6.4% in contextual understanding, with shorter outputs and zero decoding latency.
arXiv Detail & Related papers (2025-08-18T15:14:04Z)
SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models [60.72029578488467]
SpeechR is a unified benchmark for evaluating reasoning over speech in large audio-language models.<n>It evaluates models along three key dimensions: factual retrieval, procedural inference, and normative judgment.<n> Evaluations on eleven state-of-the-art LALMs reveal that high transcription accuracy does not translate into strong reasoning capabilities.
arXiv Detail & Related papers (2025-08-04T03:28:04Z)
TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation [97.54885207518946]
We introduce a novel model framework TransVIP that leverages diverse datasets in a cascade fashion. We propose two separated encoders to preserve the speaker's voice characteristics and isochrony from the source speech during the translation process. Our experiments on the French-English language pair demonstrate that our model outperforms the current state-of-the-art speech-to-speech translation model.
arXiv Detail & Related papers (2024-05-28T04:11:37Z)
A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing [31.666920933058144]
We propose our framework, Alignment-Aware Acoustic-Text Pretraining (A$3$T), which reconstructs masked acoustic signals with text input and acoustic-text alignment during training. Experiments show A$3$T outperforms SOTA models on speech editing, and improves multi-speaker speech synthesis without the external speaker verification model.
arXiv Detail & Related papers (2022-03-18T01:36:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.