mlsanityData to 14 Oct 2026

The Eloquence team submission for task 1 of MLC-SLM challenge

arXiv 2507.19308 ↗First posted 25 Jul 2025cs.SD cs.CL eess.AScited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we present our studies and experiments carried out for the task 1 of the Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM), which focuses on advancing multilingual conversational speech recognition through the development of speech language models architectures. Given the increasing relevance of real-world conversational data for building robust Spoken Dialogue Systems, we explore three approaches to multilingual ASR. First, we conduct an evaluation of the official baseline to better understand its strengths and limitations, by training two projectors (linear and qformer) with different foundation models. Second we leverage the SLAM-ASR framework to train a custom multilingual linear projector. Finally we investigate the role of contrastive learning and the extended conversational context in enhancing the robustness of recognition.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 10 of its 12 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

10 of 12 references.

References · 10

  1. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  2. 2024EuroLLM: Multilingual Language Models for Europecited by 106
  3. 2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 88
  4. 2024A Survey on Speech Large Language Models for Understandingcited by 71
  5. 2023SLM: Bridge the thin gap between speech and text foundation modelscited by 67
  6. 2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 47
  7. 2020Joint Contextual Modeling for ASR Correction and Language Understandingcited by 30
  8. 2024ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasetscited by 27
  9. 2024Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forwardcited by 17
  10. 2021Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge Distillationcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASRcited by 2
  2. 2026MEUSLI: a Multilingual Projector for LLM-based ASR and Beyondcited by 1
  3. 2026Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learningcited by 0
  4. 2026The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challengecited by 0