The virtual-to-real paradigm, ie, training models on virtual data and then applying them to
solve real-world problems, has attracted more and more attention from various domains by …

In the ongoing COVID-19 pandemic, digital technologies have played a vital role to minimize
the spread of COVID-19, and to control its pitfalls for the general public. Without such …

Both unpaired speech and text have shown to be beneficial for low-resource automatic
speech recognition (ASR), which, however were either separately used for pre-training, self …

Currently, a common approach in many speech processing tasks is to leverage large scale
pre-trained models by fine-tuning them on in-domain data for a particular application. Yet …

The rapid development of neural text-to-speech (TTS) systems enabled its usage in other
areas of natural language processing such as automatic speech recognition (ASR) or …

Adapting generic speech recognition models to specific individuals is a challenging problem
due to the scarcity of personalized data. Recent works have proposed boosting the amount …

Voice conversion (VC) aims at altering a person's voice to make it sound similar to the voice
of another person while preserving linguistic content. Existing methods suffer from a …

While end-to-end automatic speech recognition (ASR) has shown impressive performance,
it requires a huge amount of speech and transcription data. The conversion of domain …

Training of multi-speaker text-to-speech (TTS) systems relies on curated datasets based on
high-quality recordings or audiobooks. Such datasets often lack speaker diversity and are …

In this work we evaluate the utility of synthetic data for training automatic speech recognition
(ASR). We use the ASR training data to train a text-to-speech (TTS) system similar to …