# Ti-Audio: The First Multi-Dialectal End-to-End Speech LLM for Tibetan

arXiv: https://arxiv.org/abs/2604.11110 · HTML: https://mlsanity.com/paper/2604.11110/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Multilingual and low-resource ASR, one of 11 directions in Speech and audio language models.
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Placed in

- Speech and audio language models / [Multilingual and low-resource ASR](https://mlsanity.com/speech/multilingual-and-low-resource-asr/)

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [Recent Advances in Speech Language Models: A Survey](https://mlsanity.com/paper/2410.03751/) (2024)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis](https://mlsanity.com/paper/2403.01439/) (2024)
- [Tight Integrated End-to-End Training for Cascaded Speech Translation](https://mlsanity.com/paper/2011.12167/) (2020)
- [Investigating Decoder-only Large Language Models for Speech-to-text Translation](https://mlsanity.com/paper/2407.03169/) (2024)
- [Soundwave: Less is More for Speech-Text Alignment in LLMs](https://mlsanity.com/paper/2502.12900/) (2025)
- [Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages](https://mlsanity.com/paper/2508.05149/) (2025)
- [Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024](https://mlsanity.com/paper/2406.16777/) (2024)
- [When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation](https://mlsanity.com/paper/2502.00377/) (2025)
- [Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages](https://mlsanity.com/paper/2509.14804/) (2025)

## Abstract (arXiv)

Recent advances in Speech Large Language Models (Speech-LLMs) have made significant progress, greatly enhancing multimodal interaction capabilities.However, their application in low-resource and dialect-diverse environments still faces challenges. The severe scarcity of Tibetan data, coupled with the phonetic differences among its major dialects ("U-Tsang, Amdo, and Kham), is a prime example of this challenge. This paper proposes Ti-Audio, the first multi-dialectal end-to-end Speech-LLM for Tibetan. To efficiently align speech and text, we introduce a Dynamic Q-Former Adapter that extracts essential acoustic features from variable-length speech, ensuring stable cross-modal alignment even with limited data. At the data level, we leverage mutual assistance among related dialects to alleviate data scarcity and employ a temperature-based sampling strategy to maximize this synergy. Experimental results demonstrate that Ti-Audio achieves state-of-the-art performance on Tibetan benchmarks for automatic speech recognition and speech translation. Our work validates the effectiveness of cross-dialectal cooperation and provides a scalable paradigm for the development of Speech-LLM in low-resource scenarios.