machinehearing

TinyML Summit 2021

https://tinyml.org/home/index.html

Dates

Event. March 22-24, 2021

• 1. Research Symposium
• 23-24. Summit

Paper

• Submission Deadline: November 2, 2020 11:59pm AOE
• Author Notification: Jan 15th, 2021
• Camera Ready: Feb 15th, 2021

Poster / presentations

• Abstract submission due. November 11, 2020
• Acceptance. December 9, 2020
• Final submissions: February 19, 2021

Topics

In rough level of maturity/applicability

• Environmental Noise Classification on microcontrollers (thesis/NMBU)
• Acoustic Event Detection of coffeebean cracking during roasting (Roest)

• Acoustic Anomaly Detection on microcontroller for Condition Monitoring of machines (Martin/Malling)

• Monitoring of Impulse Noise for shooting ranges (PNB) No TinyML in use at the moment.
• emlearn: An open-source inference engine for microcontrollers and embedded systems (emlearn) No Soundsensing relation at the moment.

Mediums

• Poster
• Presentation
• Paper

CFP

Poster and Presentations form https://form.jotform.com/202256698202051

• Talk or poster
• Number of co-authors
• If wish to publish an aligned full paper

Paper https://openreview.net/group?id=tinyml.org/tinyML/2021/Research_Symposium

Submission plan

• Talk on ESC thesis
• 3 posters, Roest/Malling/PNB usecases
• Paper on ESC thesis

Sponsorships

https://tinyml.org/home/tinyML%20Summit%202021%20Sponsorship%20Opportunities%206-30-20.pdf

Stand, VIP dinner event, etc.

• 2.5k USD
• 5k USD
• 10k USD

Paper

Submission Page Limit. 6 - 8 pages Paper template. ACM

Topics

Relevant for us. Cut down from full list Application/usecase focused.

== tinyML Applications == Novel applications across all fields and emerging use cases Discussions about real-world use cases User behavior and system-user interaction Survey on practical experiences

== tinyML Algorithms == Deep learning and traditional machine learning algorithms Pruning, quantization, optimization methods Security and privacy implications

== tinyML Systems == Solutions that involve hardware and software co-design Characterization of tiny real-world embedded systems In-sensor processing, design, and implementation

== tinyML Evaluation == Evaluation and measurement of real production systems

emlearn only

== tinyML Software == Interpreters and code generator frameworks for tiny systems Optimizations for efficient execution Software memory optimizations

Bio

Jon Nordby is a Machine Learning Engineer with 10 years of experience developing software for embedded systems and data processing of audio and images. He holds a Bachelor’s degree in Electronics Engineering from 2010, and a Master’s degree in Data Science from 2019. His specialization is machine learning for audio and sensor data. Since 2019 he is the CTO of Soundsensing, a leading provider of IoT sensor systems using sound as the primary data source. Their systems are used for Noise Monitoring and Condition Monitoring of machinery. Jon is also the creator of emlearn, an open-source machine learning toolkit for microcontrollers and embedded devices.