The University of Southampton
Engineering

Research project: Speech Technology Lab

Currently Active: 
Yes

Our mission is to understand how we humans hear sound and to use this knowledge to develop bio-inspired devices to enhance speech understanding.

Project Overview

Model of auditory processing
Modelling auditory processing

 

Sound processing in the brain is still more successful than signal processing in silicone. A system that works as well or better than a human could lead to the next revolution in human communication. We expect that systems for assisted hearing with a broader general acceptance can only emerge from products that are used routinely by people with normal hearing. We believe that only a better understanding of the human auditory system and in consequence bio-inspired algorithms to process sound will provide the necessary breakthrough.

We aim to develop an open platform simulation system to understand and simulate human auditory perception better. The platform will provide a modelling link between brain processing and human perception. Using real time machines for signal processing we model auditory perception in the normal and impaired ear to allow an improved ability to simulate and understand sound processing, as well as being able to rapidly develop and evaluate novel signal processing algorithms to enhance speech intelligibility. Combining ‘simple' aspects, that are important for auditory object identification (pitch, space, modulation, size, etc.) with contextual information of higher statistical order, the system can be conceptualized on two levels: at a low level it provides a new way of understanding neuronal sound processing in the auditory system based on a generalization of the standard time frequency matrix which is so often used in auditory research. On a functional level, it will be useful to understand the auditory system and to simulate psychophysical auditory responses.

Picture of the speech lab team
Meet the speech lab team
Ongoing projects:
  • Using the Auditory Image Model to improve the snr of voiced sounds.
  • Combining Wiener filter and non-negative matrix factorization for improved noise reduction in non-stationary noise.
  • Using the Auditory Image Model for stable speaker recognition
  • Auditory Object identification by shape and size
  • Using non-negative matrix factorization to improve Cochlear Implant coding of speech
  • Sound localizing robot
  • Understanding sparse coding in the auditory brain stem
  • Using recordings from brain stem responses to inform sparse coding speech enhancement algorithms
  • Sound representation based on fractional derivatives

We are supported by grants from EPSRC, EU, DSTL and Google.

 

Picture of new technology prototypes
Prototypes of new technology
Researchers within the speech technology lab group:

Dr. Stefan Bleeck

Dr. Seon Man Kim

Dr. Jessica Monaghan

PhD students:

Xin Yang

Tobias Goehring

Konstantina Iliadi

 

Speech technology lab in the press:

Press release 07/03/2013

Press release 17/01/2012

Eurekalert 17/01/2012

Google grants 19/03/2013

Related research groups

Human Sciences Group
Share this research project Share this on Facebook Share this on Google+ Share this on Twitter Share this on Weibo

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×