mlsanityData to 14 Oct 2026

The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge

arXiv 2609.11724 ↗First posted 10 Sep 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper details the Eloquence team's approach to Task 2 of the 2nd MLC-SLM challenge at Interspeech 2026, which involves multilingual Multiple-Choice Question Answering (MCQA) across 21 languages. Three approaches are explored. First, we fine-tune Voxtral-Mini-3B via LoRA with cross-lingual data augmentation, ASR transcript augmentation and timestamp-aware audio cropping, achieving 0.72 macro-accuracy on evaluation Phase 2. Second, we apply multimodal in-context learning (ICL) to the frozen Voxtral-24B model to correct a strong label bias, reaching 0.81, our best result. Third, a training-free retrieval system based on a three-layer voice-anchored memory combining acoustic identity, semantic content, and a knowledge graph achieves 0.68. All three systems substantially outperform the official baseline.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 28 references that are in the map. First posted on arXiv 10 Sep 2026.

Builds on

24 of 28 references.

References · 24

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  4. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  5. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  6. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  7. 2024SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuningcited by 355
  8. 2023Powerset multi-class cross entropy loss for neural speaker diarizationcited by 111
  9. 2025MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmarkcited by 103
  10. 2024A Survey on Speech Large Language Models for Understandingcited by 71
  11. 2023SLM: Bridge the thin gap between speech and text foundation modelscited by 67
  12. 2021TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global contextcited by 62
12 more
  1. 2025Voxtralcited by 43
  2. 2025MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarioscited by 10
  3. 2025Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methodscited by 10
  4. 2025Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long Audiocited by 10
  5. 2026Closing the Modality Reasoning Gap for Speech Large Language Modelscited by 9
  6. 2025Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languagescited by 7
  7. 2025AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Taskscited by 5
  8. 2025The Eloquence team submission for task 1 of MLC-SLM challengecited by 4
  9. 2025Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Modelscited by 4
  10. 2025Benchmarking Humans and Machines on Complex Multilingual Speech Understanding Taskscited by 1
  11. 2026A Unified and Reproducible Experimentation Framework for Speech Understandingcited by 1
  12. 2026Balancing ASR and diarization in end-to-end LLMs for multi-talker speech recognitioncited by 1

Built on by

Not cited yet.