MSc thesis project proposal

[2023] Neuromorphic Real-Time Audio Denoiser

Audio denoising is a critical component in modern voice-controlled devices, digital assistants, and other audio-centric applications. The increasing demand for high-quality audio and low-power consumption necessitates the development of efficient and effective denoising techniques. This master's project aims to design, implement, and evaluate a neuromorphic hardware accelerator optimized for audio denoising tasks, taking advantage of the parallelism, low power consumption, and real-time processing capabilities of neuromorphic computing.

The project will involve a thorough investigation of existing audio denoising techniques, neuromorphic hardware architectures, and spiking neural networks (SNNs). The primary goal is to develop a hardware-software co-design approach that seamlessly integrates the neuromorphic accelerator with existing audio processing systems, ensuring compatibility and ease of deployment.

Assignment

  1. Conduct a literature review on audio denoising techniques, neuromorphic hardware architectures, and spiking neural networks.
  2. Analyze the computational and memory requirements of audio denoising algorithms to identify potential optimizations for neuromorphic hardware implementation.
  3. Design a novel neuromorphic hardware accelerator architecture optimized for audio denoising tasks.
  4. Implement a suitable spiking neural network (SNN) model for audio denoising, leveraging the capabilities of the proposed hardware accelerator.
  5. Develop a hardware-software co-design approach for integrating the neuromorphic accelerator with existing audio processing systems.
  6. Evaluate the performance of the proposed accelerator in terms of denoising quality, latency, energy consumption, and scalability, comparing it to traditional DSP and deep learning-based approaches.
  7. Document the project's findings and contribute to the development of a final report or publication.

Requirements

  1. Background in digital signal processing or audio processing.
  2. Familiarity with neuromorphic computing and hardware design.
  3. Knowledge of machine learning techniques, particularly spiking neural networks (SNNs).
  4. Proficiency in programming languages (e.g., Python, C++) and hardware description languages (e.g., VHDL, Verilog).

Contact

dr. Chang Gao

Electronic Circuits and Architectures Group

Department of Microelectronics

Last modified: 2023-03-22