KSS
Korean single-speaker TTS dataset recorded by a professional female voice actress, suitable for Korean TTS research
Duration
12 hours
Languages
1
Sample Rate
44.1 kHz
Published
2018-01
Description
1Recorded by a professional female voice actress
2Audio-aligned text sourced from books
3Approximately 12 hours of speech
4One of the most widely used single-speaker datasets in Korean TTS research
Language Details
| Language | Duration |
|---|---|
| Korean | 12 hours |
Publisher