# The Bairong System for MLC-SLM 2026: Dynamic Question-Aware Evidence Routing for Multilingual Conversational Speech Understanding

arXiv: https://arxiv.org/abs/2609.22214 · HTML: https://mlsanity.com/paper/2609.22214/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 22 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2506.04779/) (2025)
- [FunASR: A Fundamental End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2305.11013/) (2023)
- [Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension](https://mlsanity.com/paper/1804.00320/) (2018)
- [Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception](https://mlsanity.com/paper/2510.12720/) (2025)
- [HeySQuAD: A Spoken Question Answering Dataset](https://mlsanity.com/paper/2304.13689/) (2023)
- [VIBEVOICE-ASR Technical Report](https://mlsanity.com/paper/2601.18184/) (2026)
- [LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models](https://mlsanity.com/paper/2308.10390/) (2023)
- [Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods](https://mlsanity.com/paper/2509.13785/) (2025)
- [DenseLoRA: Dense Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2505.23808/) (2025)
- [Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR](https://mlsanity.com/paper/2508.01166/) (2025)
- [ReDimNet2: Scaling Speaker Verification via Time-Pooled Dimension Reshaping](https://mlsanity.com/paper/2603.11841/) (2026)
- [A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations](https://mlsanity.com/paper/2507.02927/) (2025)
- [CoDeTT: A Context-Aware Decision Benchmark for Turn-Taking Evaluation](https://mlsanity.com/paper/2603.25434/) (2026)
- [Leveraging LLM for Stuttering Speech: A Unified Architecture Bridging Recognition and Event Detection](https://mlsanity.com/paper/2505.22005/) (2025)
- [ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition](https://mlsanity.com/paper/2507.08477/) (2025)
- [Triple X: A LLM-Based Multilingual Speech Recognition System for the INTERSPEECH2025 MLC-SLM Challenge](https://mlsanity.com/paper/2507.17288/) (2025)
- [The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challenge](https://mlsanity.com/paper/2507.18051/) (2025)
- [GraphLoRA: Structure-Aware Low-Rank Adaptation for Large Language Model Recommendation](https://mlsanity.com/paper/2606.07526/) (2026)

## Abstract (arXiv)

Long multilingual conversational spoken question answering requires systems to balance long-range transcript semantics with sparse acoustic and speaker-sensitive cues. We present the Bairong system for the MLC-SLM 2026 Challenge, where a diarization-ASR front-end produces speaker-attributed transcripts and a dynamic evidence router constructs question-specific inputs for answer prediction. Instead of applying a fixed transcript-only or audio-only policy, the router infers the required evidence type and context scope from the question and answer options, and selects among full transcript context, local audio-text fusion, speaker-linked evidence, and compact global acoustic samples. This transcript-backbone design keeps discourse context available while activating audio only when it provides complementary evidence. Our Task 1 system achieves 25.70% and 18.44% tcpMER on the development and evaluation sets. For Task 2, the final system obtains 94.84% devel?opment accuracy, outperforming the full-transcript baseline by 1.68 points and the best audio-centric diagnostic system by 2.77 points. These results support dynamic question-aware routing as an effective evidence allocation strategy for conversational spoken QA.