【深度学习】TTS，LibriTTS数据集

最新推荐文章于 2025-03-17 08:30:00 发布

XD742971636

最新推荐文章于 2025-03-17 08:30:00 发布

阅读量553

点赞数

分类专栏：深度学习机器学习文章标签：深度学习人工智能

本文链接：https://blog.csdn.net/x1131230123/article/details/140998031

版权

深度学习机器学习专栏收录该内容

485 篇文章 ¥79.90 ¥99.00

订阅专栏

下载地址：
https://openslr.elda.org/resources/60/

LibriTTS 是一个包含英文音频数据的数据集。LibriTTS 数据集主要基于 LibriVox 的有声书内容，用于训练和评估文本到语音（TTS）系统。这个数据集包括高质量的录音和对应的文本转录，可以帮助开发者构建和优化 TTS 模型。

LibriTTS is a multi-speaker English corpus of approximately 585 hours of read English speech at 24kHz sampling rate, prepared by Heiga Zen with the assistance of Google Speech and Google Brain team members. The LibriTTS corpus is designed for TTS research. It is derived from the original materials (mp3 audio files from LibriVox and text files from Project Gutenberg) of the LibriSpeech corpus. The main differences from the LibriSpeech corpus are listed below:
The audio files are at 24kHz sampling rate.
The speech is split at sentence breaks.
Both orig

了解本专栏