כתבה
arXiv cs.CL ·
Eloquence ב-MLC-SLM 2026
The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge
קבוצת Eloquence הציגה שלוש גישות ל-Task 2 של MLC-SLM 2026, כולל fine-tuning של Voxtral-Mini-3B ולמידה multimodal. התוצאות עלו על הבסליין הרשמי.
תקציר מקורי באנגליתarXiv:2609.11724v1 Announce Type: new 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. Al
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית