Multi-Source Evidence Fusion for Audio Question Answering

TL;DR

This paper presents a multi-source ensemble system for audio question answering that generates verifiable reasoning chains by integrating multiple acoustic tools and language models, achieving top performance in the Interspeech 2026 challenge.

Contribution

It introduces a novel multi-source evidence fusion pipeline that enhances reasoning transparency and accuracy in audio question answering systems.

Findings

Ranked first in the Interspeech 2026 challenge

Outperformed all competitors in reasoning quality

Produced dense, verifiable reasoning chains

Abstract

Large audio language models (LALMs) can answer questions about speech, music, and environmental sounds, yet their internal reasoning is largely opaque and difficult to validate. We describe TalTech's solution to the Agent Track of the Interspeech 2026 Audio Reasoning Challenge, in which systems are evaluated on reasoning process quality, specifically the factual accuracy, logical soundness, and completeness of their reasoning chains. Our multi-source ensemble pipeline uses two LALMs that generate independent observations, while a separate text-only reasoning model cross-checks these against outputs from 25 acoustic tools organized into reliability tiers. By grounding every inference step in explicit, reliability-tagged evidence, the system produces dense, verifiable reasoning chains. Our system ranked first in the challenge, outperforming all competing systems by a wide margin in challenge's reasoning quality metric.