StyleStream 2.0:快速、可控的串流語音風格轉換
StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion
StyleStream 2.0 以少步 MeanFlow 模型降低串流語音轉換延遲,並透過統一的 flow matching 模型支援文字語音設計及指令式語音編輯。系統在消費級 GPU 上的端到端延遲為 520 ms,速度較 StyleStream 1.0 快 2 倍,同時維持轉換品質。評測顯示,其目標風格保真度表現突出,在可懂度及非編輯屬性保留方面亦具競爭力。
Published on Oct 20
Authors:
,
Abstract
StyleStream 2.0 improves streaming voice conversion with lower latency via a few-step MeanFlow model and enables text-based voice design and editing through a unified flow matching model.
Voice style conversion (VSC) aims to transform a source utterance to match the timbre, accent, and emotion of a target voice while preserving linguistic content. StyleStream 1.0 introduced the first streamable zero-shot VSC system with state-of-the-art conversion quality, but remained limited in two ways: approximately 1s end-to-end latency on consumer hardware, and the lack of a text-based interface for designing or editing target voices. We present StyleStream 2.0, a fast and controllable streaming VSC framework that addresses these limitations. To reduce latency, we train a few-step pixel MeanFlow model and further fine-tune it with autoregressive feedback inspired by Self Forcing, improving robustness under streaming inference. This reduces end-to-end latency to 520~ms on a consumer GPU, a 2x speedup over StyleStream 1.0, while maintaining conversion quality. To enable controllable style manipulation, we remove the mel-spectrogram context and instead route target style information through a compact style embedding. In this embedding space, we train a unified text-conditioned flow matching model that supports both text-based voice design, which maps natural language prompts to voice styles, and instruction-based voice editing, which modifies a specific attribute of a source utterance while preserving the rest. Experiments show that StyleStream 2.0 achieves the strongest target style fidelity on VSC, voice design, and voice editing, while remaining competitive on intelligibility and non-edited attribute preservation.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.28940
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/2610.28940 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/2610.28940 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/2610.28940 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