Sign up to save your podcasts
Or
Share A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models
🤗 Upvotes: 42 | cs.CL, cs.SD, eess.AS
Authors:
Kirill Borodin, Nikita Vasiliev, Vasiliy Kudryavtsev, Maxim Maslov, Mikhail Gorodnichev, Oleg Rogov, Grach Mkrtchian
Title:
A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models
Arxiv:
http://arxiv.org/abs/2507.13563v1
Abstract:
Russian speech synthesis presents distinctive challenges, including vowel reduction, consonant devoicing, variable stress patterns, homograph ambiguity, and unnatural intonation. This paper introduces Balalaika, a novel dataset comprising more than 2,000 hours of studio-quality Russian speech with comprehensive textual annotations, including punctuation and stress markings. Experimental results show that models trained on Balalaika significantly outperform those trained on existing datasets in both speech synthesis and enhancement tasks. We detail the dataset construction pipeline, annotation methodology, and results of comparative evaluations.
View all episodes
By Jingwen Liang, Gengyu Wang🤗 Upvotes: 42 | cs.CL, cs.SD, eess.AS
Authors:
Kirill Borodin, Nikita Vasiliev, Vasiliy Kudryavtsev, Maxim Maslov, Mikhail Gorodnichev, Oleg Rogov, Grach Mkrtchian
Title:
A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models
Arxiv:
http://arxiv.org/abs/2507.13563v1
Abstract:
Russian speech synthesis presents distinctive challenges, including vowel reduction, consonant devoicing, variable stress patterns, homograph ambiguity, and unnatural intonation. This paper introduces Balalaika, a novel dataset comprising more than 2,000 hours of studio-quality Russian speech with comprehensive textual annotations, including punctuation and stress markings. Experimental results show that models trained on Balalaika significantly outperform those trained on existing datasets in both speech synthesis and enhancement tasks. We detail the dataset construction pipeline, annotation methodology, and results of comparative evaluations.