Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Dissecting a Low Power AI/ML Edge Application - Noise Suppression

tinyML via YouTube

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a comprehensive analysis of low-power AI/ML edge applications for noise suppression in this 27-minute conference talk from the tinyML Summit 2022. Delve into the evolution of noise suppression algorithms, from traditional spectral-subtraction methods to advanced RNN and Transformer-based approaches. Examine the challenges of deploying computationally demanding AI/ML algorithms in battery-powered devices like earbuds and mobile phones. Learn about an example RNN-based Noise Suppression algorithm and discover how offloading ML processing from a DSP to an ML-optimized IP can significantly reduce energy consumption. Gain insights into a robust software framework that enables developers to combine traditional and ML-based processing functions for optimal user experience. The talk covers key topics including virtual meetings, video conferencing fatigue, software optimization, latency and energy considerations, and software development strategies for noise suppression applications.

Syllabus

Introduction
Virtual meetings
Video conferencing fatigue
Agenda
Challenges
Noise Suppression
Overview
Demonstration
Holistic Approach
Software Optimization
Latency and Energy
Software Development
Conclusion
Sponsors

Taught by

tinyML

Reviews

Start your review of Dissecting a Low Power AI/ML Edge Application - Noise Suppression

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.