Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2512.22491 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914221916160000 |
|---|---|
| author | Wang, Suhua Wang, Zifan Sun, Xiaoxin Wang, D. J. Liu, Zhanbo Li, Xin |
| author_facet | Wang, Suhua Wang, Zifan Sun, Xiaoxin Wang, D. J. Liu, Zhanbo Li, Xin |
| contents | 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%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22491 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text Representation Wang, Suhua Wang, Zifan Sun, Xiaoxin Wang, D. J. Liu, Zhanbo Li, Xin Computation and Language Artificial Intelligence 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%. |
| title | ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text Representation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2512.22491 |