# SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge

arXiv: https://arxiv.org/abs/2507.03343 · HTML: https://mlsanity.com/paper/2507.03343/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 26 references that are in the map.
- First posted on arXiv 4 Jul 2025.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling](https://mlsanity.com/paper/2311.00430/) (2023)
- [MinMo: A Multimodal Large Language Model for Seamless Voice Interaction](https://mlsanity.com/paper/2501.06282/) (2025)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR](https://mlsanity.com/paper/2406.06619/) (2024)
- [MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems](https://mlsanity.com/paper/2307.11394/) (2023)
- [ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets](https://mlsanity.com/paper/2406.08641/) (2024)
- [Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition](https://mlsanity.com/paper/2307.05956/) (2023)
- [Mixture-of-Expert Conformer for Streaming Multilingual ASR](https://mlsanity.com/paper/2305.15663/) (2023)
- [Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts](https://mlsanity.com/paper/2311.01070/) (2023)
- [Anatomy of Industrial Scale Multilingual ASR](https://mlsanity.com/paper/2404.09841/) (2024)
- [Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets](https://mlsanity.com/paper/2405.02132/) (2024)
- [MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research](https://mlsanity.com/paper/2406.18301/) (2024)
- [SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR](https://mlsanity.com/paper/2406.18021/) (2024)
- [Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text](https://mlsanity.com/paper/2409.11214/) (2024)
- [SAML: Speaker Adaptive Mixture of LoRA Experts for End-to-End ASR](https://mlsanity.com/paper/2406.19706/) (2024)
- [BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR](https://mlsanity.com/paper/2501.12602/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR](https://mlsanity.com/paper/2601.00557/) (2026)

## Abstract (arXiv)

This paper describes SHNU multilingual conversational speech recognition system (SHNU-mASR, team name-"maybe"), submitted to Track 1 of the INTERSPEECH 2025 MLC-SLM Challenge. Our system integrates a parallel-speech-encoder architecture with a large language model (LLM) to form a unified multilingual ASR framework. The parallel-speech-encoder consists of two pre-trained encoders, the Whisper-large-v3 encoder and mHuBERT-147 encoder. Their output embeddings are concatenated and fed into the LLM, enabling the model to leverage complementary acoustic and linguistic knowledge and achieve competitive performance. Moreover, we adopt a tri-stage training strategy to jointly update the low-rank adaptation modules and projector parameters of both the speech encoders and the LLM. In addition, we incorporate an additional language-aware prompt at the LLM input to enhance language-specific text generation. The SHNU-mASR system achieves an overall character/word error rate (CER/WER) of 11.76% on the blind evaluation set of the challenge, outperforming the official MLC-SLM baseline by 8.41 absolute CER/WER, without increasing the baseline training data.