# Multi-Source Evidence Fusion for Audio Question Answering

Source: [Multi-Source Evidence Fusion for Audio Question Answering](<https://www.sota2.com/research/paper/69bb83060636e5bf4afc19f2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-20T05:00:12.244Z

Authors: Aivo Olev, Tanel Alum\\"ae

Published: 2026-03-18T15:12:42.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Audio Reasoning on MMAR Agent Track](<https://www.sota2.com/research/sota/audio-reasoning-on-mmar-agent-track.md>): Audio Reasoning; MMAR Agent Track; Accuracy: 76.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.17822>)

[PDF](<https://arxiv.org/pdf/2603.17822.pdf>)