mlsanityData to 14 Oct 2026

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

arXiv 2609.22214 ↗First posted 2 Sep 2026cs.CL cs.SDcited by 0

Not on the map. Why?

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.

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

21 of 22 references.

References · 21

  1. 2025Qwen3-Omni Technical Reportcited by 497
  2. 2026Qwen3.5-Omni Technical Reportcited by 174
  3. 2026Qwen3-ASR Technical Reportcited by 118
  4. 2025MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmarkcited by 103
  5. 2023FunASR: A Fundamental End-to-End Speech Recognition Toolkitcited by 95
  6. 2018Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehensioncited by 74
  7. 2025Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perceptioncited by 30
  8. 2023HeySQuAD: A Spoken Question Answering Datasetcited by 16
  9. 2026VIBEVOICE-ASR Technical Reportcited by 16
  10. 2023LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Modelscited by 14
  11. 2025Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methodscited by 10
  12. 2025DenseLoRA: Dense Low-Rank Adaptation of Large Language Modelscited by 4
9 more
  1. 2025Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASRcited by 4
  2. 2026ReDimNet2: Scaling Speaker Verification via Time-Pooled Dimension Reshapingcited by 3
  3. 2025A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversationscited by 2
  4. 2026CoDeTT: A Context-Aware Decision Benchmark for Turn-Taking Evaluationcited by 2
  5. 2025Leveraging LLM for Stuttering Speech: A Unified Architecture Bridging Recognition and Event Detectioncited by 1
  6. 2025ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognitioncited by 1
  7. 2025Triple X: A LLM-Based Multilingual Speech Recognition System for the INTERSPEECH2025 MLC-SLM Challengecited by 1
  8. 2025The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challengecited by 1
  9. 2026GraphLoRA: Structure-Aware Low-Rank Adaptation for Large Language Model Recommendationcited by 1

Built on by

Not cited yet.