- Technology
- Artificial Intelligence
- Neural Networks
- Recurrent Neural Networks (RNN)
- Long short-term memory (LSTM)
- STEM
- Engineering
- Electrical Engineering
- Signal Processing
- Digital Signal Processing
- Audio Processing
- STEM
- Engineering
- Electrical Engineering
- Signal Processing
- Digital Signal Processing
- Audio Processing
- Audio Effects
Leveraging Pruning and Quantization for Efficient Real-Time Audio Applications
ADC - Audio Developer Conference via YouTube
Master AI and Machine Learning: From Neural Networks to Applications
Live Online Classes in Design, Coding & AI — Small Classes, Free Retakes
Overview
Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Explore the crucial model compression techniques of pruning and quantization for efficient real-time audio applications in this conference talk from ADCx India 2024. Discover how these methods can significantly reduce computational complexity and memory usage while maintaining high performance in resource-constrained environments. Learn about various pruning methodologies, quantization processes, and their impact on sophisticated audio models for tasks such as real-time audio effects, audio style transfer, and source separation. Gain insights into implementing these techniques to enhance the efficiency of complex audio processing models, enabling robust real-time performance even on devices with limited resources.
Syllabus
Leveraging Pruning & Quantization for Real-Time Audio Applications - Dharanipathi Rathna Kumar
Taught by
ADC - Audio Developer Conference