FLEURS-R：面向生成任务的修复后多语言语音语料库
FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks
AI总结：
本文提出语音修复后的多语言并行语料库FLEURS-R，基于FLEURS用Miipher模型提升102种语言语音的质量与保真度，可推动低资源语言语音生成研究，且已公开发布。
摘要：
本文介绍了FLEURS-R，它是语音通用表示少样本学习评估（FLEURS）语料库的语音修复应用版本。FLEURS-R保留了FLEURS涵盖102种语言的N路并行语音语料库，通过应用语音修复模型Miipher提升了音频质量与保真度。FLEURS-R的目标是推动更多语言的语音技术发展，促进低资源语言下的文本转语音（TTS）及其他语音生成任务等领域的研究。使用修复后的语音与基于新语料库训练的TTS基线模型开展的综合评估表明，新语料库在保留语音语义内容的同时，显著提升了语音质量。该语料库已通过Hugging Face公开发布。
英文摘要：
This paper introduces FLEURS-R, a speech restoration applied version of the Few-shot Learning Evaluation of Universal Representations of Speech (FLEURS) corpus. FLEURS-R maintains an N-way parallel speech corpus in 102 languages as FLEURS, with improved audio quality and fidelity by applying the speech restoration model Miipher. The aim of FLEURS-R is to advance speech technology in more languages and catalyze research including text-to-speech (TTS) and other speech generation tasks in low-resource languages. Comprehensive evaluations with the restored speech and TTS baseline models trained from the new corpus show that the new corpus obtained significantly improved speech quality while maintaining the semantic contents of the speech. The corpus is publicly released via Hugging Face.
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。
