E2 TTS：极其简单的完全非自回归零样本文本转语音
E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
AI总结：
本研究提出完全非自回归的零样本TTS系统E2 TTS，以音频填充任务训练基于流匹配的梅尔频谱生成器，无需额外组件与复杂技术，性能达到当前最优，还具备输入表示灵活性并推出多种推理优化变体。
摘要：
本文提出了Embarrassingly Easy Text-to-Speech（E2 TTS，极其简单的文本转语音）系统，这是一款完全非自回归的零样本文本转语音系统，具备人类水平的自然度，以及达到当前最优水平的说话人相似度与可懂度。在E2 TTS框架中，文本输入会被转换为带有填充标记的字符序列，随后基于音频填充任务，训练基于流匹配的梅尔频谱图生成器。与过往诸多研究不同，该系统无需额外组件（如时长模型、字素转音素模块），也无需复杂技术（如单调对齐搜索）。尽管结构简单，E2 TTS的零样本TTS性能达到了当前最优水平，与Voicebox、NaturalSpeech 3等过往研究相当甚至更优。E2 TTS的简洁性还让输入表示具备灵活性，本文提出了多种E2 TTS变体以提升推理阶段的易用性。演示样本可参见https://aka.ms/e2tts/。
英文摘要：
This paper introduces Embarrassingly Easy Text-to-Speech (E2 TTS), a fully non-autoregressive zero-shot text-to-speech system that offers human-level naturalness and state-of-the-art speaker similarity and intelligibility. In the E2 TTS framework, the text input is converted into a character sequence with filler tokens. The flow-matching-based mel spectrogram generator is then trained based on the audio infilling task. Unlike many previous works, it does not require additional components (e.g., duration model, grapheme-to-phoneme) or complex techniques (e.g., monotonic alignment search). Despite its simplicity, E2 TTS achieves state-of-the-art zero-shot TTS capabilities that are comparable to or surpass previous works, including Voicebox and NaturalSpeech 3. The simplicity of E2 TTS also allows for flexibility in the input representation. We propose several variants of E2 TTS to improve usability during inference. See https://aka.ms/e2tts/ for demo samples.
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。
