Roman Korostik

According to our database1, Roman Korostik authored at least 8 papers between 2019 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
Robust Speech Recognition with Schrödinger Bridge-Based Speech Enhancement.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Modifying Flow Matching for Generative Speech Enhancement.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024
Schrödinger Bridge for Generative Speech Enhancement.
Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

2023
Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

2021
Assessing Speaker Interpolation in Neural Text-to-Speech.
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.
Proceedings of the 13th International Congress on Image and Signal Processing, 2020

2019
The STC text-to-speech system for Blizzard Challenge 2019.
Proceedings of the Blizzard Challenge 2019, Vienna, Austria, September 23, 2019, 2019


  Loading...