Building a Neuromorphic Auditory Pathway for Sensing the Surrounding Environment

Supervisors:

Primary supervisor: Dr. Ying Xu
Co-supervisor Professor André van Schaik

Description:

Western Sydney University (WSU) is seeking a highly motivated and creative PhD student to work with Neuromorphic Engineering pioneer, Professor André van Schaik, and the team at the International Centre for Neuromorphic Systems (ICNS) on a project to design a neuromorphic auditory system to perform sensing tasks in real-world environments.

This need for neuromorphic auditory systems is motivated by the ease with which humans and animals perform perceptual tasks such as detecting anomalous sounds or segregating different sound streams in noisy environments. In the human auditory pathway, information is extracted and conveyed through sequences of action potentials, or spikes. The spike streams form robust representations for encoding information that is important for perception. The human sensory system achieves real-time, low-power, and robust performance by operating in such an asynchronous “event”-based way.

To investigate the signal processing and mimic the efficiency of the human auditory system, the PhD candidate will develop a neuromorphic auditory pathway that can extract and cluster acoustic features and capture higher-level cognitive executive functions for solving real-world problems.

Outcomes:

Investigation of neuromorphic feature extraction and clustering approaches to sound processing, auditory scene analysis, and anomaly detection.
Investigation of a neuromorphic auditory system based on the feature extraction and clustering stage to build up expectations of how sound streams evolve over time. This will be used for attentional selectivity (e.g., the cocktail party problem) and sound prediction.
Investigation of a real-time implementation of a neuromorphic auditory pathway that has a potential to be integrated into current devices and systems and then applied to solving real-world problems.

What does the scholarship provide?

Domestic candidates receive a tax-free stipend of $31,828 (AUD) per annum for up to 3.5 years to support living costs, supported by the Research Training Program (RTP) Fee Offset.
International candidates receive a tax-free stipend of $31,828 (AUD) per annum for up to 3.5 years to support living costs. Those with a strong track record will be eligible for a tuition fee waiver.
Support for conference attendance, fieldwork, and additional costs as approved by MARCS.

International candidates are required to hold an Overseas Student Health Care (OSHC) insurance policy for the duration of their study in Australia. This cost is not covered by the scholarship.

Eligibility criteria:

The successful applicant should:

Hold qualification and experience equal to one of the following 1) a coursework Master’s with at least 25% research component, 2) a research Master’s degree, or 3) equivalent international qualifications in electrical engineering or computer science.
Demonstrated expertise using Verilog or VHDL for FPGA programming or experience with Python for network design and testing.
Have a background in signal processing.
Not hold a PhD degree in any field.
Be conversational in written and spoken English.
Reside in Australia for the duration of their studies, except for periods of approved overseas study leave.
Not receive income from another source to support general living costs while undertaking the program, if that income is greater than 75% of the stipend rate*.
Be enthusiastic and motivated to undertake further study at the PhD level.

* The 75% rule referenced above does not apply to: a) income earned from sources unrelated to research or b) income related to the research but not for the purpose of supporting general living costs. International applicants must demonstrate English language proficiency.

International applicants must demonstrate English language proficiency.