About

About the SAP Laboratory

Speech and audio processing research in the Communications and Signal Processing Group at Imperial College London is addressing the fundamental science of speech and audio processing as well as technology applications particularly in telecoms and audio interfaces.

Recent topic areas include echo cancellation, dereverberation, speech enhancement, SIMO MIMO acoustic system identification, speech recognition, blind source separation extraction, speaker verification, speech analysis, Digital Audio Broadcast (DAB).

Current Projects

Hearing aids (new)

Developing speech enhancement algorithms that jointly enhance the speech received by the two ears

Read more...

Robot Audition

We provide autonomous agents with a situational awareness of sound sources and reflectors in the acoustic environment.

Read more...

IEEE-AASP Challenge on Localization & Tracking (LOCATA)

Open-source data corpus and benchmarking challenge for sound source localization & tracking algorithms.

Read more...

Audio Diarization

We develop novel algorithms to address the question “who spoke when?”

Read more...

Blind System Identification

We extract information from multichannel systems for dereverberation and source recovery.
Read more...

Acoustic Imaging

We are investigating methods to characterise rough surfaces from acoustic reflections.

Read more...

News

End of term social!

Instead of our usual end-of-term social, SAP group enjoyed a virtual pub quiz to celebrate! Congratulations to Peter for winning!

New Intern: Welcome to Anselm Lohmann

We are delighted to welcome our new Undergraduate Intern, Anselm Lohmann. Anselm’s research interest lies in the use of machine learning systems for signal processing applications. His current work as an undergraduate intern in the ELO-SPHERES project involves developing machine learning solutions for adaptive beamforming in hearing aids.

Farewell lunch for Christine

The SAP group wishes Christine all the very best for her future plans and career at the University of Southampton. New personal webpage: https://www.ecs.soton.ac.uk/people/ce1r20 Good luck, Christine!

SAP Paper at ICASSP 2020

We are delighted that the following paper has been accepted for ICASSP 2020 in Barcelona, Spain in May 2020. [1] Vincent W. Neo, Christine Evers and Patrick A. Naylor, “PEVD-based speech enhancement in reverberant environments, ” in Proc. IEEE Int. Conf. on Acoust., Speech and Signal Process. (ICASSP), 2020. See you online on 7 May 2020!

SPiN 2020 Poster Presentation

We are delighted that Alastair Moore and Rebecca Vos presented the following poster: ‘Evaluation of The Performance of a Model-Based Adaptive Beamformer’.

HiPEDS Poster Presentation

We are delighted that Aidan Hogg presented the following poster: ‘Audio Diarization in the Cocktail Party Scenario’.

Congratulations to Prof Patrick Naylor

Congratulations to Prof Patrick Naylor who has been elevated to IEEE Fellow from 1 Jan 2020 for contributions to signal processing for speech dereverberation and analysis!

Sponsors

Collaborations