将人声转为动物或设计音效，支持44.1kHz高保真输出
When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds
- 设计新预处理流程与改进的条件变分自编码模型
- 在质量、自然度和相似度上均优于基线方法
- 适合语音合成、创意音频生成等场景使用
人类到非人类语音转换（H2NH-VC）可将人声转化为动物或设计类发声。不同于以往仅关注犬吠声及16kHz或22.05kHz音频的研究，本文拓展至更广泛的非语音声音，包括狮子吼叫、鸟鸣等自然声与合成咆哮等设计音。为实现多样化非语音声音生成及44.1kHz高质量音频转换，提出新的预处理流程与优化的基于条件变分自编码器（CVAE）的H2NH-VC模型，兼顾人声与非人声特性。实验表明，该方法在主观评分（MOS）中于质量、自然度和相似度上均优于基线，有效实现多种非人声音色的语音转换。演示样本见https://nc-ai.github.io/speech/publications/nonhuman-vc/
原文摘要 · Abstract (English)
Human to non-human voice conversion (H2NH-VC) transforms human speech into animal or designed vocalizations. Unlike prior studies focused on dog-sounds and 16 or 22.05kHz audio transformation, this work addresses a broader range of non-speech sounds, including natural sounds (lion-roars, birdsongs) and designed voice (synthetic growls). To accomodate generation of diverse non-speech sounds and 44.1kHz high-quality audio transformation, we introduce a preprocessing pipeline and an improved CVAE-based H2NH-VC model, both optimized for human and non-human voices. Experimental results showed that the proposed method outperformed baselines in quality, naturalness, and similarity MOS, achieving effective voice conversion across diverse non-human timbres. Demo samples are available at https://nc-ai.github.io/speech/publications/nonhuman-vc/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。