AccentBox: 向高保真零样本口音生成迈进
AccentBox: Towards High-Fidelity Zero-Shot Accent Generation
AI总结:
AccentBox通过两阶段流程实现高保真零样本口音生成,提升口音识别与生成的准确性和多样性。
摘要:
尽管最近的零样本文本到语音(ZS-TTS)模型在自然度和说话人相似性方面取得了高成就,但在口音保真度和控制方面仍存在不足。为了解决这个问题,我们提出了零样本口音生成,将外国口音转换(FAC)、带口音的TTS和ZS-TTS统一起来,提出了一种新颖的两阶段流程。在第一阶段,我们在未见过的说话人上实现了最先进的(SOTA)在口音识别(AID)上的0.56 F1分数。在第二阶段,我们基于AID模型提取的预训练说话人无关口音嵌入条件化一个ZS-TTS系统。所提出的系统在固有/跨口音生成中实现了更高的口音保真度,并实现了未见过的口音生成。
英文摘要:
While recent Zero-Shot Text-to-Speech (ZS-TTS) models have achieved high naturalness and speaker similarity, they fall short in accent fidelity and control. To address this issue, we propose zero-shot accent generation that unifies Foreign Accent Conversion (FAC), accented TTS, and ZS-TTS, with a novel two-stage pipeline. In the first stage, we achieve state-of-the-art (SOTA) on Accent Identification (AID) with 0.56 f1 score on unseen speakers. In the second stage, we condition a ZS-TTS system on the pretrained speaker-agnostic accent embeddings extracted by the AID model. The proposed system achieves higher accent fidelity on inherent/cross accent generation, and enables unseen accent generation.
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。