# PART: Progressive Alignment Representation Training for Multilingual Speech-To-Text with LLMs

arXiv: https://arxiv.org/abs/2509.19745 · HTML: https://mlsanity.com/paper/2509.19745/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 23 of 23)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [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)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Listen, Think, and Understand](https://mlsanity.com/paper/2305.10790/) (2023)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs](https://mlsanity.com/paper/2407.04051/) (2024)
- [CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus](https://mlsanity.com/paper/2002.01320/) (2020)
- [Advocating Character Error Rate for Multilingual ASR Evaluation](https://mlsanity.com/paper/2410.07400/) (2024)
- [Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?](https://mlsanity.com/paper/2402.12025/) (2024)
- [Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning](https://mlsanity.com/paper/2409.19510/) (2024)
- [AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation](https://mlsanity.com/paper/2312.02512/) (2023)
- [LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models](https://mlsanity.com/paper/2407.15415/) (2024)
- [Investigating Decoder-only Large Language Models for Speech-to-text Translation](https://mlsanity.com/paper/2407.03169/) (2024)
- [How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not](https://mlsanity.com/paper/2409.17044/) (2024)
- [Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024](https://mlsanity.com/paper/2406.16777/) (2024)
- [Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling](https://mlsanity.com/paper/2412.16474/) (2024)
- [VHASR: A Multimodal Speech Recognition System With Vision Hotwords](https://mlsanity.com/paper/2410.00822/) (2024)
- [Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis](https://mlsanity.com/paper/2505.18972/) (2025)
- [Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems](https://mlsanity.com/paper/2506.13596/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have expanded from text to speech, giving rise to Speech Large Models (SLMs) that support recognition, translation, and synthesis. A key challenge is aligning speech and text representations, which becomes harder in multilingual settings. Existing methods often freeze LLM parameters and train encoders on multilingual data, but this forces cross-language convergence and limits performance. We introduce Progressive Alignment Representation Training (PART), a multi-stage and multi-task framework that separates within-language from cross-language alignment. During cross-language training, LLM parameters are dynamically activated, and text-based tasks are later introduced to enhance multilingual understanding. Experiments on CommonVoice 15, Fleurs, Wenetspeech, and CoVoST2 show that PART surpasses conventional approaches, with analysis confirming its ability to balance language-specific distinctions and cross-language generalization. These results demonstrate PART's effectiveness and generality for multilingual speech modality alignment.