Spotkanie po długiej przerwie

Plan spotkania:

• Staszek Raczyński z firmy PICTEC będzie miał prezentację pt: "Systemy uczące się w macierzach mikrofonowych"

• Adam Nadolski z Amazon będzie miał preznetację pod tytułem: "Machine Learning in Text-to-Speech: Grapheme-to-Phoneme Conversion Problem"

Stanisław is a researcher working on machine learning and signal processing since 2006. He got his PhD from the University of Tokyo in 2011 in music information retrieval (in particular multiple pitch estimation, eigeninstruments, harmony modeling, music similarity, genre recognition), a field on which he also spend his post-doctoral fellowship in INRIA, France. He currently works as an assistant professor at Gdańsk University of Technology and is a vice-president and a senior researcher at a non-public research institute PICTEC, where he deals with multichannel signal processing.

Adam Nadolski is a Researcher working in Amazon TTS Team in Gdansk. He has worked in TTS since late 2011. Since then he's been both contributing to new languages development (Danish, Russian, Swedish, German) and research on modeling for TTS (e.g. automatic phrasing, G2P improvements, phoneme mapping, DNN-based models for prosody modeling). Adam earned his PhD from Gdansk Univ. of Technology in 2005, for his research in graph coloring and scheduling problems.