InstructTTSEval
收藏资源简介:
InstructTTSEval是一个全面的基准测试,旨在评估文本到语音(TTS)系统遵循复杂自然语言风格指令的能力。该数据集提供了一个分层评估框架,包含三个逐步挑战性的任务,测试低级别声学控制和高级别风格泛化能力。
InstructTTSEval is a comprehensive benchmark designed to evaluate the ability of text-to-speech (TTS) systems to follow complex natural language style instructions. This dataset provides a hierarchical evaluation framework, which includes three progressively challenging tasks that test low-level acoustic control and high-level style generalization capabilities.
InstructTTSEval 数据集概述
数据集简介
- 名称:InstructTTSEval
- 类型:文本转语音(TTS)系统评估基准
- 目的:评估TTS系统在遵循复杂自然语言风格指令方面的能力
核心特点
- 评估框架:分层设计,包含三个逐步挑战性任务
- 测试能力:
- 低级别声学控制
- 高级别风格泛化
数据来源
- 托管平台:Hugging Face
- 访问地址:https://huggingface.co/datasets/CaasiHUANG/InstructTTSEval
相关文献
- 论文标题:InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
- arXiv地址:https://arxiv.org/abs/2506.16381
- PDF版本:https://arxiv.org/pdf/2506.16381
引用格式
bibtex @misc{huang2025instructttsevalbenchmarkingcomplexnaturallanguage, title={InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems}, author={Kexin Huang and Qian Tu and Liwei Fan and Chenchen Yang and Dong Zhang and Shimin Li and Zhaoye Fei and Qinyuan Cheng and Xipeng Qiu}, year={2025}, eprint={2506.16381}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2506.16381}, }




