MOSS-VoiceGenerator：通过自然语言描述生成逼真声音
MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions
AI总结：
本文提出MOSS-VoiceGenerator，通过自然语言描述生成逼真声音，解决现有模型依赖 studio 数据导致缺乏真实人声特点的问题。
摘要：
语音设计从自然语言生成说话者音色旨在直接从自由形式文本描述生成语音，允许用户创建针对特定角色、个性和情绪定制的声音。此类可控的语音生成对下游应用如讲故事、游戏配音、角色扮演代理和对话助手具有广泛意义。然而，现有模型大多训练于精心录制的录音室数据，生成的语音干净清晰但缺乏真实人声的生动特质。为解决这些限制，我们提出MOSS-VoiceGenerator，一个开源的指令驱动语音生成模型，直接从自然语言提示生成新音色。受真实世界声音变化产生更自然语音的假设启发，我们训练于大规模表达性语音数据，源自电影内容。主观偏好研究证明其在整体表现、指令遵循和自然度方面优于其他语音设计模型。
英文摘要：
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.
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。
