The IEEE Signal Processing Society cordially invites you to a lecture by Dr Tomohiro Nakatani, IEEE Distinguished Industry Speaker. The event will take place on 27 February 2026 at 11:00 am in lecture hall L3.204 at Paderborn University.
Under the title "Enhancing Distant Automatic Speech Recognition via Model-Based Multi-Microphone Front-Ends", the lecture is dedicated to automatic speech recognition with far-field recorded audio signals. This technology is a key requirement for applications such as recognising natural conversations in real everyday environments. Interference factors such as background noise, reverberation and overlapping speakers pose a particular challenge.
Dr Nakatani gives an overview of model-based multi-microphone front-ends that are used to suppress such interference. A key advantage of these methods is their ability to decompose audio signals using physical and probabilistic models - often without prior training. This makes them particularly suitable for unknown and complex acoustic environments. In combination with neural networks, these approaches enable high-precision signal processing even under difficult conditions.
Using challenging scenarios of Distant Automatic Speech Recognition, the presentation will show how dereverberation, noise reduction and source separation methods can significantly improve recognition performance.
Dr Tomohiro Nakatani is a Senior Distinguished Researcher at the Communication Science Laboratories of NTT Corporation in Japan. He is one of the leading international researchers in the field of audio signal processing and robust automatic speech recognition. His best-known contributions include the Weighted Prediction Error (WPE), cACGMM and SpeakerBeam methods. He was named an IEEE Fellow in 2021 for his work.
The event will be moderated by Prof. Dr Reinhold Häb-Umbach (Paderborn University) and Prof. Dr Gerald Enzner (IEEE SPS Germany Chapter).
The lecture will take place in Building L, Room L3.204 of Paderborn University.
Event date
