36 citations · 47 across the 4 of their papers we have counts for
4 papers
Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
Pin-Jui Ku, Alexander H. Liu, Roman Korostik +3
This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coeffi…
Schrödinger Bridge for Generative Speech Enhancement
Ante Jukić, Roman Korostik, Jagadeesh Balam +1
This paper proposes a generative speech enhancement model based on Schrödinger bridge (SB). The proposed model is employing a tractable SB to formulate a data-to-data process betwe…
Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
Vladimir Bataev, Roman Korostik, Evgeny Shabalin +2
We propose an end-to-end Automatic Speech Recognition (ASR) system that can be trained on transcribed speech data, text-only data, or a mixture of both. The proposed model uses an…
You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation
Aleksandr Laptev, Roman Korostik, Aleksey Svischev +3
Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing…