PulseAugur
实时 20:21:45

新框架ProPS从文本提示合成说话人嵌入

研究人员开发了ProPS,一个用于合成由自然语言提示条件化的说话人嵌入的新框架。该系统将说话人资料的文本描述转换为句子嵌入,然后指导混合密度网络在x-vector空间中预测高斯混合模型。ProPS已证明其能够生成准确反映所需属性(如年龄、性别、口音和韵律)的说话人嵌入分布,使其对于文本到语音(Text-To-Speech)和语音转换(Voice Conversion)等可控语音生成系统具有价值。 AI

影响 为TTS和语音转换等应用实现更可控、更细致的语音生成。

排序理由 该集群包含一篇描述用于合成说话人嵌入的新框架的研究论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新框架ProPS从文本提示合成说话人嵌入

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Thomas Thebaud, Junhyeok Lee, Laureano Moro-Velazquez, Jesus Villalba Lopez, Najim Dehak ·

    ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions

    arXiv:2607.05276v1 Announce Type: cross Abstract: Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather than generative: they map an observed speech segmen…

  2. arXiv cs.AI TIER_1 English(EN) · Najim Dehak ·

    ProPS:用于自然语言条件说话人嵌入分布的提示式剖面合成

    Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather than generative: they map an observed speech segment to an x-vector, which is then used for downstrea…