2019/06/26 by Lenar Gabdrakhmanov, Gabdrakhmanov, Lenar, Rustem Garaev +3 · 2 citations
Computer Science · Engineering · Mathematics · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #I.2.7 #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Sound (cs.SD) #cs.LG #cs.SD #eess.AS #electronic engineering #information engineering #msc:I.2.7 #stat.ML
paper · pdf · doi:10.48550/arxiv.1906.11645
Accepted to SPECOM'2019
arxiv created 2019/06/26 · arxiv updated 2019/06/28
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.