Data: 24 de março
Hora: 13h
Local: Anfiteatro PA2, Pavilhão de Matemática, Campus Alameda
Orador: Ben Peters (INESC-ID)
Título: “What’s in a speech token?”
Resumo:
Discrete speech tokenization is a surprisingly effective technique to adapt text language models to speech. But despite the simplicity of the method, the nature of the units it produces is not widely understood. In this talk, I ask some questions (and hopefully answer a few) about how, when, and why discrete speech tokens work.
Nota biográfica:
Ben Peters is a postdoctoral researcher at INESC-ID. He works at the intersection of NLP and speech.
A Priberam integra a Comunidade IST Spin-Off®.
Os “Priberam Machine Learning Lunch Seminars” são de entrada livre, mediante inscrição prévia.
