Sep 2026· 2nd Workshop on Multilingual Conversational Speech Language Model (MLC-SLM 2026)· pp. 47-51· 1 citation· 28 references
Computer Science
TL;DR
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, is detailed, which involves multilingual Multiple-Choice Question Answering across 21 languages.
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.
This paper describes our systems for the Multilingual Conversational Speech Language Model (MLC-SLM) Challenge 2026. The challenge contains two tasks: multilingual conversational transcription with speaker attribution, and multiple-choice conversational speech understanding. For Task 1, we use MOSS Transcribe Diarize (...
Han-Fu Chen, Chenchen Yang, Zheng-Yu Lin et al.· 2nd Workshop on Multilingual...· 0 citations
We present our submission to the BabyLM 2026 Multilingual Shared Task. Our system uses OLMo2, a modern decoder-only architecture with grouped-query attention, RoPE, and SwiGLU, trained from scratch on the official BabyLM trilingual corpus (English, Dutch, Chinese). We employ a hybrid training ob-jective following (Char...
Zi-Chao Wei· Proceedings of the Second Ba...· 0 citations
Experimental results demonstrate that the cascaded system remains more reliable under the MLC-SLM Task 1 conditions, while unified speech LLMs offer a promising direction for future speaker-attributed ASR.
This paper describes the TUM-Heilbronn sys-tem submission to the WMT26 Multilingual Instruction Shared Task (MIST). The MIST covers three tasks: context-based question answering, open-ended generation, and cross-lingual summarization to evaluate the multi-lingual instruction-following ability of large language models....
Jen-Chien Hou, Tsedeniya Kinfe Temesgen, Alexander Fraser· Proceedings of the Eleventh...· 1 citation
In this paper, we describe Cake By VPBank’s system submitted to Task I - Multilingual Conversational Speech Recognition of the 2nd MLC-SLM Challenge, reaching 15.84% time-constrained permutation word error rate (tcpWER) on the blind 21-variant, 14-language evaluation set. Rather than change the model architecture, we a...
Thuc Tran Huu, Nhat M. Nguyen, Huan Ho Kha Viet· 2nd Workshop on Multilingual...· 0 citations
We present ArA-DF 2026, the first shared task for Arabic speech deepfake detection, held at ArabicNLP 2026. Unlike existing benchmarks that conflate all distribution shift into a single evaluation set, ArA-DF 2026 separates dialect generalization (Track 1: unseen Arabic dialects and speakers) from acoustic robustness (...
Vasista Sai Lodagala, Y. El Kheir, Sara Althubaiti et al.· Proceedings of The Fourth Ar...· 0 citations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
