MathWorks, the maker of MATLAB and Simulink, will be hosting the next BISH Bash on Thursday, May 15th! Join us for an evening of talks, networking and delicious bites. Please see below for the agenda and abstracts.
Please mark "attend" to let us know you are attending. Please write a comment to let us know whether you will be attending in person or virtually, as we are planning a quality dinner for all in-person attendees. All attendees will receive a virtual meeting link. We look forward to seeing you there! (3975 Freedom Circle, Santa Clara, CA 95054, directions below)
Agenda
- 6:00pm: Networking
- 6:30pm: Modeling acoustic devices and enclosures -- Francis Tiong
- 7:00pm: Room Acoustics Simulation with MATLAB -- Jihad Ibrahim
- 7:25pm: Rapid prototyping of Pytorch/Python AI Applications with MATLAB/Simulink -- Adam Cook
- 7:50pm: Sound quality evaluation
- 8:15pm: more networking
Abstracts
- Modeling acoustic devices and enclosures
A device that converts electrical signals into audible sound is inherently nonlinear. In the context of internet appliances, it is essential to accurately model this nonlinearity to enhance overall performance. The frequency response of a loudspeaker, for example, can vary significantly based on its enclosure design. Similarly, modeling the behavior of earphones that fit directly onto the ear presents its own set of challenges. Acoustic device modeling is both a fascinating and rewarding endeavor. In this session, we will explore the modeling of acoustic devices, including techniques for tuning loudspeaker enclosures.
- Room Acoustics Simulation with MATLAB and Audio Toolbox
In this presentation, we explore techniques for simulating sound propagation within a room using MATLAB and Audio Toolbox. We delve into geometric methods such as stochastic ray tracing and the image-source method, which provide efficient and intuitive ways to model sound reflections and paths. Additionally, we examine physics-based approaches including the finite element method (FEM) and finite-difference time-domain (FDTD) methods, which offer detailed and accurate simulations by solving complex wave equations. By comparing these methods, we highlight their respective advantages and applications in room acoustics, providing insights into selecting the appropriate technique for various acoustic scenarios.
- Rapid prototyping of Pytorch/Python AI Application with MATLAB/Simulink
MATLAB and Simulink offer the ability to seamlessly integrate AI networks developed with Pytorch and other open-source deep learning frameworks. These AI systems can be thoroughly tested and efficiently deployed to embedded systems for rapid prototyping and production workflows. We will demonstrate the workflow for the deployment of a smart speaker model to two different common embedded platforms, Raspberry Pi and Qualcomm Hexagon.
How satisfactory is the sound quality, or conversely, how irritating is the noise? Both subjective and objective assessments can aid in quantifying the experience. For instance, in developing noise reduction strategies, having an instant score would be beneficial for efficient regression tuning. This session will explore various valuable metrics relevant to this field.
Directions
3975 Freedom Circle, Santa Clara, CA 95054
The event will be held on the walk-in level of the building. If you are coming from 101 freeway, take the Great America Pkwy exit. There is a huge parking structure beside the building and it is free. A simple map is attached blow. EV charging (not free) is available also.
