用自然语言生成真实感语音，让声音更贴近真人表现。
MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions
- 基于自然语言指令直接生成语音音色，无需录音
- 在影视级语料上训练，提升声音真实感与表现力
- 适合角色配音、虚拟助手等需要个性化语音的场景
从自然语言生成语音旨在直接根据自由文本描述生成说话人音色，使用户能为特定角色、个性或情绪定制声音。这种可控制的声音生成对故事讲述、游戏配音、角色扮演代理和对话助手等下游应用具有重要意义，是现代文本转语音模型的重要任务。然而，现有模型主要在精心录制的录音棚数据上训练，生成的语音虽清晰准确，却缺乏真实人类声音的生活质感。为此，我们提出MOSS-VoiceGenerator，一个开源的指令驱动语音生成模型，可直接从自然语言提示生成新音色。受‘接触真实声学变化能产生更自然感知声音’的假设启发，我们在大规模来自影视内容的表达性语音数据上进行训练。主观偏好测试表明，该模型在整体性能、指令遵循能力及自然度方面均优于其他语音设计模型。
原文摘要 · Abstract (English)
Voice design from natural language aims to generate speaker timbres directly from free-form textual descriptions, allowing users to create voices tailored to specific roles, personalities, and emotions. Such controllable voice creation benefits a wide range of downstream applications-including storytelling, game dubbing, role-play agents, and conversational assistants, making it a significant task for modern Text-to-Speech models. However, existing models are largely trained on carefully recorded studio data, which produces speech that is clean and well-articulated, yet lacks the lived-in qualities of real human voices. To address these limitations, we present MOSS-VoiceGenerator, an open-source instruction-driven voice generation model that creates new timbres directly from natural language prompts. Motivated by the hypothesis that exposure to real-world acoustic variation produces more perceptually natural voices, we train on large-scale expressive speech data sourced from cinematic content. Subjective preference studies demonstrate its superiority in overall performance, instruction-following, and naturalness compared to other voice design models.
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。