# ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text Representation

arXiv: https://arxiv.org/abs/2512.22491 · HTML: https://mlsanity.com/paper/2512.22491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 27 Dec 2025.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 6 of 6)

- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search](https://mlsanity.com/paper/2005.11129/) (2020)
- [Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model](https://mlsanity.com/paper/2502.09533/) (2025)
- [Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation](https://mlsanity.com/paper/2411.11295/) (2024)
- [Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super Resolution](https://mlsanity.com/paper/2409.09337/) (2024)
- [SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow](https://mlsanity.com/paper/2504.07776/) (2025)

## Abstract (arXiv)

As an endangered language, Manchu presents unique challenges for speech synthesis, including severe data scarcity and strong phonological agglutination. This paper proposes ManchuTTS(Manchu Text to Speech), a novel approach tailored to Manchu's linguistic characteristics. To handle agglutination, this method designs a three-tier text representation (phoneme, syllable, prosodic) and a cross-modal hierarchical attention mechanism for multi-granular alignment. The synthesis model integrates deep convolutional networks with a flow-matching Transformer, enabling efficient, non-autoregressive generation. This method further introduce a hierarchical contrastive loss to guide structured acoustic-linguistic correspondence. To address low-resource constraints, This method construct the first Manchu TTS dataset and employ a data augmentation strategy. Experiments demonstrate that ManchuTTS attains a MOS of 4.52 using a 5.2-hour training subset derived from our full 6.24-hour annotated corpus, outperforming all baseline models by a notable margin. Ablations confirm hierarchical guidance improves agglutinative word pronunciation accuracy (AWPA) by 31% and prosodic naturalness by 27%.