PFluxTTS：融合流匹配TTS的混合系统，具备稳健的跨语言语音克隆和推理时模型融合
PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual Voice Cloning and Inference-Time Model Fusion
AI总结：
PFluxTTS通过双解码器设计、序列语音提示嵌入和改进的PeriodWave vocoder，解决了流匹配TTS在稳定性与自然性平衡、跨语言语音克隆和低速率梅尔特征音频质量方面的不足，实现了更自然的语音合成和更高的语音相似度。
摘要：
我们提出了PFluxTTS，一种混合的文本到语音系统，旨在解决流匹配TTS的三个缺口：稳定性与自然性的权衡、弱的跨语言语音克隆以及低速率梅尔特征带来的音频质量限制。我们的贡献包括：（1）一种双解码器设计，通过推理时的向量场融合结合持续引导和对齐自由模型；（2）使用基于FLUX的解码器中的语音提示嵌入序列实现稳健的克隆，跨语言保持说话人特征，无需提示转录；（3）一种改进的PeriodWave vocoder，具有超分辨率到48kHz。在跨语言真实数据上，PFluxTTS明显优于F5-TTS、FishSpeech和SparkTTS，与ChatterBox在自然度（MOS 4.11）相当，但实现23%更低的WER（6.9% vs. 9.0%），并超越ElevenLabs在说话人相似度（+0.32 SMOS）。该系统在大多数开源模型失败的挑战性场景中仍保持稳健，仅需短参考音频且无需额外训练。音频演示可在https://braskai.github.io/pfluxtts/获取。
英文摘要：
We present PFluxTTS, a hybrid text-to-speech system addressing three gaps in flow-matching TTS: the stability-naturalness trade-off, weak cross-lingual voice cloning, and limited audio quality from low-rate mel features. Our contributions are: (1) a dual-decoder design combining duration-guided and alignment-free models through inference-time vector-field fusion; (2) robust cloning using a sequence of speech-prompt embeddings in a FLUX-based decoder, preserving speaker traits across languages without prompt transcripts; and (3) a modified PeriodWave vocoder with super-resolution to 48 kHz. On cross-lingual in-the-wild data, PFluxTTS clearly outperforms F5-TTS, FishSpeech, and SparkTTS, matches ChatterBox in naturalness (MOS 4.11) while achieving 23% lower WER (6.9% vs. 9.0%), and surpasses ElevenLabs in speaker similarity (+0.32 SMOS). The system remains robust in challenging scenarios where most open-source models fail, while requiring only short reference audio and no extra training. Audio demos are available at https://braskai.github.io/pfluxtts/
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。
