Showing eess.ASShow all
2 papers · 1 filter
eess.AS2024
Transcribe, Align and Segment: Creating speech datasets for low-resource languages
Taras Sereda
In this work, we showcase a cost-effective method for generating training data for speech processing tasks. First, we transcribe unlabeled speech using a state-of-the-art Automatic…
eess.AS2024★ 1 cited
Pheme: Efficient and Conversational Speech Generation
Paweł Budzianowski, Taras Sereda, Tomasz Cichy +1
In recent years, speech generation has seen remarkable progress, now achieving one-shot generation capability that is often virtually indistinguishable from real human voice. Integ…