Algorithms for Automatic Accentuation and Transcription of Russian Texts in Speech Recognition Systems

Yakovenko, Olga; Bondarenko, Ivan; Borovikova, Mariya; Vodolazsky, Daniil

doi:10.1007/978-3-319-99579-3_78

Search citation statements

Order By: Relevance

Paper Sections

Select...

Speech Corpus1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2019

2021

Publication Types

Select...

Book1

Other1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The frequency distribution for the phonemes are provided in Figure 1. Phonemic transcription was performed as suggested in [25].…”

Section: Speech Corpusmentioning

confidence: 99%

RUSLAN: Russian Spoken Language Corpus for Speech Synthesis

Gabdrakhmanov¹,

Garaev²,

Razinkov³

2019

Speech and Computer

View full text Add to dashboard Cite

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.

show abstract

“…The frequency distribution for the phonemes are provided in Figure 1. Phonemic transcription was performed as suggested in [25].…”

Section: Speech Corpusmentioning

confidence: 99%