The University of Auckland

Project #14: Investigating loudspeaker/microphone configuration for real-time speech masking system

Back

Description:

Speech masking is a technique being used to hide confidential information in a target speech where a jammer sound (called masking sound) is played to hinder understanding by the human auditory system. Since the masking sound could cause annoyance for listeners, the supervisor’s team has been working on a research that will identify a novel design of masking system that will NOT cause any psychological disruptions to the listeners while maintaining its masking performance by investigating the target speech. To this end, so far the team has discovered a few novel design of masking sound but the most effective way for projecting the masking sound to the listeners as well as collecting the target speech is still unknown. This final year project will focus on the effective configuration of loudspeakers/microphones used to generate and project the masking sound. The projects will include setting up an experimental rig using audio devices (i.e. loudspeakers, microphones, audio interface) and programmes to generate a masking sound, running subjective listening tests to evaluate the performance of each configuration, and analysis of the listening tests.

Students suitable for this project would be interested in acoustics and digital signal processing as well as some aspects of human science and arts such as audiology, psychology, and linguistics. At least one of the group members must have passed MECHENG370 after 2015. 

Type:

Undergraduate

Outcome:

A working real-time speech masking system using multiple microphones and loudspeakers.
A set of data collected from subjective listening tests and results of subsequent statistical analysis.

Prerequisites

At least one of the group members must have passed MECHENG370 after 2015.
Having done MECHENG313 is also a plus (not a requirement).

Specialisations

Categories

Supervisor

Team

Lab

Acoustics Lab (City 422.154, Lab)