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

• URL: http://arxiv.org/abs/2609.11724v1
• Date: Thu, 10 Sep 2026 15:41:11 GMT
• Title: The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge
• Abstract summary: We fine-tune Voxtral-Mini-3B via LoRA with cross-lingual data augmentation, ASR transcript augmentation and timestamp-aware audio cropping.<n>Second, we apply multimodal in-context learning to the frozen Voxtral-24B model to correct a strong label bias, reaching 0.81.<n>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.
• Score: 7.980139831363608
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SEAR: Segment-Evidence-Aware Routing for Weak-to-Strong Multilingual Speech MCQ [0.0]
  This paper describes our system for Task2 of the second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge.<n>A language model converts timestamped ASR into coherent event spans, which are expanded by a boundary margin and cropped from the original recording.<n>A text-only probe partitions the data into weak, text-answerable items used for supervised fine-tuning and strong, audio-dependent items used for reinforcement learning.
  arXiv  Detail & Related papers  (2026-09-10T10:38:19Z)
• Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge [28.363948904202932]
  The second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge evaluates two tasks over complete, unsegmented multilingual conversations.<n>Neither task provides oracle utterance boundaries or speaker labels at evaluation, and Task 2 provides no question-answer training set.<n>We fine-tune VibeVoice-ASR-7B with random leading-silence cropping, consistent timestamp correction, and distribution-matched augmentation.
  arXiv  Detail & Related papers  (2026-08-14T10:00:42Z)
• An Omnilingual-ASR-Based Speech-LLM System for the 2nd MLC-SLM Challenge [0.0]
  We describe a cascaded diarization-then-recognition system that combines DiariZen-Large-s80 (WavLM-Large) segmentation, embedding-based two-adapted clustering, and a LoRA- omniASR LLM 7B v2 recognizer.<n>On the official Development set (150 conversations, 21 language/accent categories), the system attains a macroMER of 29.27%, versus 79.15% for the official baseline; on the Evaluation set it scores 50.23%.
  arXiv  Detail & Related papers  (2026-07-14T07:52:39Z)
• Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech [14.048968602801606]
  This paper describes our self-designed hallucination system for Task 1 of the MLC-SLM 2026 Challenge for multilingual two-speaker conversational speech.<n>The system combines a modular speaker diarization front end with a challenge-adapted Qwen3-ASR-1.7B recognizer.
  arXiv  Detail & Related papers  (2026-07-09T08:07:34Z)
• Bilingual Text-to-Motion Generation: A New Benchmark and Baselines [52.71312720094036]
  We introduce BiHumanML3D, the first bilingual text-to-motion benchmark, constructed via LLM-assisted annotation and rigorous manual correction.<n>We also propose a simple yet effective baseline, Bilingual Motion Diffusion synthesis (BiMD), featuring Cross-Lingual Alignment (CLA)<n>BiMD with CLA achieves an FID of 0.045 vs. 0.169 and R@3 of 82.8% vs. 80.8%, significantly outperforms monolingual diffusion models and translation baselines on BiHumanML3D.
  arXiv  Detail & Related papers  (2026-03-26T08:48:27Z)
• LFM2 Technical Report [87.58431408281973]
  We present LFM2, a family of Liquid Foundation Models designed for efficient on-device deployment and strong task capabilities.<n>The LFM2 family covers 350M-8.3B parameters, including dense models (350M, 700M, 1.2B, 2.6B) and a mixture-of-experts variant (8.3B total, 1.5B active)<n>We build multimodal and retrieval variants: LFM2-VL for vision-latency tasks, LFM2-Audio for speech, and LFM2-ColBERT for retrieval.
  arXiv  Detail & Related papers  (2025-11-28T17:56:35Z)
• Transsion Multilingual Speech Recognition System for MLC-SLM 2025 Challenge [18.816408172588144]
  This paper presents the architecture and performance of a novel Multilingual Automatic Speech Recognition (ASR) system developed by the Transsion Speech Team for Track 1 of the MLC-SLM 2025 Challenge.<n>The proposed system comprises three key components: 1) a frozen Whisper-large-v3 based speech encoder, leveraging large-scale pretraining to ensure robust acoustic feature extraction.<n>By systematically combining pretrained models with task specific fine-tuning, the system achieved a word/character error rate (WER/CER) of 9.83% across 11 languages in the evaluation set and ranked third place among global participants.
  arXiv  Detail & Related papers  (2025-08-15T10:39:05Z)
• MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognition [62.89464258519723]
  We propose a multi-layer cross-attention fusion based AVSR approach that promotes representation of each modality by fusing them at different levels of audio/visual encoders. Our proposed approach surpasses the first-place system, establishing a new SOTA cpCER of 29.13% on this dataset.
  arXiv  Detail & Related papers  (2024-01-07T08:59:32Z)
• MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning [90.17500229142755]
  The first Multimodal Emotion Recognition Challenge (MER 2023) was successfully held at ACM Multimedia. This paper introduces the motivation behind this challenge, describe the benchmark dataset, and provide some statistics about participants. We believe this high-quality dataset can become a new benchmark in multimodal emotion recognition, especially for the Chinese research community.
  arXiv  Detail & Related papers  (2023-04-18T13:23:42Z)
• M3ST: Mix at Three Levels for Speech Translation [66.71994367650461]
  We propose Mix at three levels for Speech Translation (M3ST) method to increase the diversity of the augmented training corpus. In the first stage of fine-tuning, we mix the training corpus at three levels, including word level, sentence level and frame level, and fine-tune the entire model with mixed data. Experiments on MuST-C speech translation benchmark and analysis show that M3ST outperforms current strong baselines and achieves state-of-the-art results on eight directions with an average BLEU of 29.9.
  arXiv  Detail & Related papers  (2022-12-07T14:22:00Z)
• Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition [55.25565305101314]
  Articulatory features are invariant to acoustic signal distortion and have been successfully incorporated into automatic speech recognition systems. This paper presents a cross-domain and cross-lingual A2A inversion approach that utilizes the parallel audio and ultrasound tongue imaging (UTI) data of the 24-hour TaL corpus in A2A model pre-training. Experiments conducted on three tasks suggested incorporating the generated articulatory features consistently outperformed the baseline TDNN and Conformer ASR systems.
  arXiv  Detail & Related papers  (2022-06-15T07:20:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.