Effectiveness of Dual-Microphone Model-Based Speech Discrimination for Increasing Speech Intelligibility in In-Situ Babble Noise

Malaspina Labs Inc. conducts applied research and development of state-of-the-art audio processing
technologies that dramatically increase speech comprehension in noisy environments. Based in
Vancouver Canada, Malaspina Labs is driven by a core team of academic and industry researchers in
the fields of audio processing and speech isolation. We have a common goal of developing the
world’s most advanced speech processing software and implementing it on milliwatt-class target
devices. Malaspina Labs has demonstrated the effectiveness of its VoiceBoost™ model based
speech discrimination for ultra-low power mobile processors. By isolating speech-of-interest from
background noise including background speech, VoiceBoost™ has been shown to improve speech
quality by 36% over existing 3G phone and network noise reduction in real-world high noise
environments. This research internship project will advance the field for speech intelligibility and noise
reduction as well as the company’s audio processing technologies.

Faculty Supervisor:

Lorienne Jenstad

Student:

Partner:

Malaspina Labs

Discipline:

Life Sciences

Sector:

Professional, scientific and technical services

University:

The University of British Columbia

Program: