Linguistic Cues for the Extraction and Synthesis of Speech in Extreme Noise

Malaspina Labs Inc. develops algorithms for enhancing speech in extremely noisy audio signals for real-time applications such as hearing aids and mobile devices. Many classical approaches to speech enhancement are not applicable to these domains because of severe hardware and psychoacoustics constraints such as far-field, single microphone use cases (no beamforming), <=10 millisecond latency between input and output (1/10th the time of a blink of an eye) due to bone conduction acoustic feedback, <=40 MIPs CPU processing requirements (1/100th of the processing power of a smartphone) due to battery life constraints, and <=100 Kilobyte algorithm memory requirements (1 millionth of the memory of a current generation smartphone) due to target device memory constraints. The proposed project aims to extend Malaspina’s proprietary algorithms by exploiting linguistic cues to infer or constrain the detection of speech components in extreme noise while respecting the constraints of the target devices.

Faculty Supervisor:

Molly Babel

Student:

Partner:

Malaspina Labs

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

The University of British Columbia

Program: