Next Tech Talk: Dr Yong Xu from the University of Surrey

Written by
Dr Sacha Krstulović, Director, AA Labs

October 27, 2017

We are delighted to announce the speaker for our next free Tech Talk lecture.

Dr Yong Xu from the Making Sense of Sounds project at the University of Surrey will be talking about ‘Deep learning based speech and audio signal processing’ on November 28th at our offices in Cambridge. Doors open at 18:30 and the talk beings promptly at 18:45.

Dr Xu said: “In this talk, I will firstly give a summary of my previous deep learning based speech enhancement and noise robust speech recognition work. This work focused on how to improve the generalisation capacity of the deep learning-based system. Then I will mainly introduce my recent post-doc work at the University of Surrey, where I am involving in the “making sense of sounds” project under the supervision of Prof. Mark D. Plumbley. The idea of weakly-supervised sound event detection will be presented. Our winning system in the ‘Large-scale weakly supervised sound event detection for smart cars’ task of Detection and Classification of Acoustic Scenes and Events (DCASE) 2017 challenge will also be covered.”

More on Dr Yong Xu:

Dr Yong Xu is a research fellow in University of Surrey, UK. He got his PhD degree from University of Science and Technology of China (USTC) in 2015. He once visited Georgia Institute of Technology, USA from September 2014 to May 2015. After his PhD graduation, he worked for IFLYTEK as a researcher from April 2015 to April 2016. His papers have obtained 630+ citations with two ESI highly cited IEEE journal papers. He won the 1st place in DCASE 2017 challenge for ‘Large-scale weakly supervised sound event detection for smart cars’.

To register for this free event visit our MeetUp website.

Adding more personality to personal assistants

Read more

Audio Analytic announces partnership with Hive

Read more

Gartner highlights sound recognition as a high-impact use for AI-powered smartphones

Read more

Our software

Our embedded software platform, ai3™, is integrated into consumer products to make them more intelligent by understanding the sounds around them.

Find out more

Use cases

Our sound recognition software has been designed to work in a wide range of products from light bulbs, to smart speakers and beyond.

Read more