Data-driven speech and language technology: from small to large (language) models

Lecture given by Hermann Ney, RWTH Aachen University

Abstract: Today data-driven methods like neural networks and deep learning are widely used for speech and language processing. We will re-visit the evolution of these methods over the last 40 years and try to present a unifying view of their principles. Specifically the talk will focus on speech recognition and language modelling.

Biography: Hermann Ney is a full professor of computer science with RWTH Aachen University, Germany. Previously, he headed the Speech Recognition Group, Philips Research. His main research interests include the area of statistical methods for pattern recognition and human language technology and their specific applications to speech recognition, machine translation, and image object recognition. In particular, he has worked on dynamic programming for continuous speech recognition, language modeling, and phrase-based approaches to machine translation. He has authored and coauthored more than 600 papers in journals, books, conferences, and workshops.

Mots clés : ai data-driven method deep learning machine translation speech and language processing speech recognition