Roman Korostik

According to our database, Roman Korostik authored at least 5 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration.

Pin-Jui Ku, Alexander H. Liu, Roman Korostik, Sung-Feng Huang, Szu-Wei Fu, Ante Jukic

CoRR, 2024

2023

Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator.

Vladimir Bataev, Roman Korostik, Evgeny Shabalin, Vitaly Lavrukhin, Boris Ginsburg

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

2021

Assessing Speaker Interpolation in Neural Text-to-Speech.

Roman Korostik, Javier Latorre, Sivanand Achanta, Yannis Stylianou

Proceedings of the Speech and Computer - 23rd International Conference, 2021

2020

You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation.

Aleksandr Laptev, Roman Korostik, Aleksey Svischev, Andrei Andrusenko, Ivan Medennikov, Sergey Rybin

Proceedings of the 13th International Congress on Image and Signal Processing, 2020

2019

The STC text-to-speech system for Blizzard Challenge 2019.

Roman Korostik, Artem Chirkovskiy, Alexey Svischev, Ilya Kalinovskiy, Andrey Talanov

Proceedings of the Blizzard Challenge 2019, Vienna, Austria, September 23, 2019, 2019