RUSLAN: Russian Spoken Language Corpus for Speech Synthesis
This provides a valuable resource and baseline for Russian speech synthesis, but it is incremental as it applies existing methods to a new language-specific dataset.
The authors tackled the problem of text-to-speech synthesis for Russian by creating RUSLAN, a large open corpus with 31 hours of single-speaker audio, and trained an end-to-end neural network that achieved MOS scores of 4.05 for naturalness and 3.78 for intelligibility.
We present RUSLAN -- a new open Russian spoken language corpus for the text-to-speech task. RUSLAN contains 22200 audio samples with text annotations -- more than 31 hours of high-quality speech of one person -- being the largest annotated Russian corpus in terms of speech duration for a single speaker. We trained an end-to-end neural network for the text-to-speech task on our corpus and evaluated the quality of the synthesized speech using Mean Opinion Score test. Synthesized speech achieves 4.05 score for naturalness and 3.78 score for intelligibility on a 5-point MOS scale.