mlsanityData to 14 Oct 2026

Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models

arXiv 2506.13300 ↗First posted 16 Jun 2025cs.CL cs.AI cs.SDcited by 0

On the map: LLM reasoning → Audio-language model reasoning

Abstract (arXiv)

This paper presents Seewo's systems for both tracks of the Multilingual Conversational Speech Language Model Challenge (MLC-SLM), addressing automatic speech recognition (ASR) and speaker diarization with ASR (SD-ASR). We introduce a multi-stage training pipeline that explicitly enhances reasoning and self-correction in speech language models for ASR. Our approach combines curriculum learning for progressive capability acquisition, Chain-of-Thought data augmentation to foster intermediate reflection, and Reinforcement Learning with Verifiable Rewards (RLVR) to further refine self-correction through reward-driven optimization. This approach achieves substantial improvements over the official challenge baselines. On the evaluation set, our best system attains a WER/CER of 11.57% for Track 1 and a tcpWER/tcpCER of 17.67% for Track 2. Comprehensive ablation studies demonstrate the effectiveness of each component under challenge constraints.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 24 of its 34 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

24 of 34 references.

References · 24

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  4. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  5. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  6. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  7. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 426
  8. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  9. 2024GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinementscited by 103
  10. 2023CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Maskingcited by 102
  11. 2022Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkitcited by 97
  12. 2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 88
12 more
  1. 2023Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenizationcited by 87
  2. 2023An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verificationcited by 42
  3. 2025Reasoning Language Models: A Blueprintcited by 42
  4. 2024Instruction Tuning With Loss Over Instructionscited by 40
  5. 2018Deep-FSMN for Large Vocabulary Continuous Speech Recognitioncited by 28
  6. 2020CN-Celeb: multi-genre speaker recognitioncited by 27
  7. 2024Instruction Fine-Tuning: Does Prompt Loss Matter?cited by 26
  8. 2024VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmarkcited by 26
  9. 20243D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarizationcited by 16
  10. 2025Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakerscited by 16
  11. 2023VoxBlink: A Large Scale Speaker Verification Dataset on Cameracited by 9
  12. 2025GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systemscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
  2. 2026SEAR: Segment-Evidence-Aware Routing for Weak-to-Strong Multilingual Speech MCQ
  3. 2025Customizing Speech Recognition Model with Large Language Model Feedback
  4. 2026Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech
  5. 2025Explore the Reinforcement Learning for the LLM based ASR and TTS system
  6. 2025The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challenge
  7. 2023Multi-stage Large Language Model Correction for Speech Recognition
  8. 2026Data-Efficient On-Policy Distillation for Automatic Speech Recognition