Abstract Recently, we have seen tremendous progress in the field of language models (LMs), with the release of numerous open models and closed API systems. However, fewer and fewer disclose how they are created: Which[…]
Abstract Despite many recent developments in speaker diarization, it remains a challenge and an active area of research to make diarization robust and effective in real-life scenarios. End-to-end neural speaker diarization (EEND) systems are considered[…]
Abstract This talk will cover three different directions of my research journey in the speech domain: recognition, generation and privacy. We will start with self-training algorithms that have recently emerged as a powerful strategy for[…]
Click here for the complete schedule and more information.
Click here for the complete schedule and more information.
Abstract Large language models (LMs) are pretrained on diverse data sources—news, discussion forums, books, online encyclopedias. A significant portion of this data includes facts and opinions which, on one hand, celebrate democracy and diversity of[…]
