SEAM:面向低資源 TTS 的頻譜嵌入對齊與合併
SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS
SEAM 透過頻譜篩選和嶺迴歸,從已知子詞嵌入初始化未見 token,為低資源 TTS 擴展詞彙。研究涵蓋三種語言和兩種 TTS 架構,使用最多少四倍的訓練數據,仍可接近或達到基準表現;相較隨機初始化和平均池化,樣本複雜度降低 75%。
Published on Oct 19
Authors:
,
,
Abstract
SEAM initializes unseen token embeddings from subtokens via spectral filtering and ridge regression, reducing training data needs by 75% for low-resource text-to-speech vocabulary expansion.
Expanding the vocabulary of conditional text-to-speech (TTS) models typically requires extensive fine-tuning with paired audio, creating a major bottleneck for low-resource and cross-lingual adaptation. To address this, we introduce SEAM, a zero-audio initialization method that constructs embeddings for unseen tokens from known subtokens. Unlike standard pooling strategies that ignore sequential structure, SEAM applies a spectral filter to preserve temporal phonetic order and uses closed-form ridge regression to align the new embeddings with the pretrained conditioning manifold. Across three languages and two TTS architectures, SEAM approaches or matches baseline performance using up to four times less training data, reducing sample complexity by 75\% compared to random initialization and mean pooling. Our approach provides a lightweight, reproducible, and theoretically grounded solution for vocabulary expansion in low-resource speech synthesis.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.26252
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.26252 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.26252 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.26252 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co