arXiv 2610.28940 · cs.SD · 2026-10-20
StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion
Yisi Liu, Nicholas Lee, Gopala K. Anumanchipalli
UC Berkeley
在最新榜 #345 本站收录于 2026-10-26
一句话要点
StyleStream 2.0 是流式语音风格转换系统，用少步 MeanFlow 加自回归反馈微调，把消费级 GPU 上的端到端延迟降到 520 毫秒（比 1.0 快一倍），并加入文本设计目标音色的接口。
StyleStream 2.0 is a streaming voice style conversion system that cuts end-to-end latency on a consumer GPU to 520 ms (2x faster than 1.0) using a few-step MeanFlow model with autoregressive feedback, and adds a text interface for designing target voices.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：高效训练与推理
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation ▲511
- Scaling Properties of Same-Family On-Policy Distillation ▲327
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲250
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
同机构：UC Berkeley
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。