arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2506.16580cs.CLcs.SDeess.AS

流式非自回归口音转换与发音改善模型

Streaming Non-Autoregressive Model for Accent Conversion and Pronunciation Improvement

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Carnegie Mellon University(卡内基梅隆大学)

Tuan-Nam Nguyen, Ngoc-Quan Pham, Seymanur Akti, Alexander Waibel

AI总结:

提出首个流式口音转换模型,通过Emformer编码器和优化推理实现流式处理,结合TTS生成训练数据,在保持稳定延迟下性能媲美顶尖模型。

摘要:

我们提出了首个流式口音转换(AC)模型,该模型在保留说话人身份和韵律的同时,将非母语语音转换为接近母语的口音,并改善发音。我们的方法通过使用Emformer编码器和优化的推理机制修改先前的AC架构,实现了流式处理。此外,我们整合了一个原生文本到语音(TTS)模型来生成理想的真实数据,以实现高效训练。我们的流式AC模型在保持稳定延迟的同时,达到了与顶尖AC模型相当的性能,成为首个能够进行流式处理的AC系统。

英文摘要:

We propose a first streaming accent conversion (AC) model that transforms non-native speech into a native-like accent while preserving speaker identity, prosody and improving pronunciation. Our approach enables stream processing by modifying a previous AC architecture with an Emformer encoder and an optimized inference mechanism. Additionally, we integrate a native text-to-speech (TTS) model to generate ideal ground-truth data for efficient training. Our streaming AC model achieves comparable performance to the top AC models while maintaining stable latency, making it the first AC system capable of streaming.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑