Overview
Using deep learning in speech and audio poses important computational challenges when transitioning from research models to real-world designs. The need to work in a wide range of operating conditions requires large training datasets, and implementing designs on low-power embedded devices requires exploration to find the optimal parameters and the right trade-offs between prediction performance and computational complexity.
In this webinar, we’ll show how to use MATLAB and NVIDIA GPUs to build deep networks, accelerate data-intensive problems, and train multiple network configurations in parallel.
During the session you will learn about:
- Designing and importing deep networks for speech and audio applications
- Using data augmentation to synthesize additional application-specific training data
- Extracting most commonly used features from speech and audio signals
- Training deep learning models on NVIDIA GPUs and NVIDIA GPU Cloud (NGC)
About the Presenter
Gabriele Bunkheila is a senior product manager at MathWorks for audio and DSP applications. After joining MathWorks in 2008, he worked as a signal processing application engineer for several years, supporting MATLAB and Simulink users across industries from algorithm design to real-time implementations. Before MathWorks, he held a number of research and development positions, and he was a lecturer of sound theory and technologies at the national film school of Rome. He has a master’s degree in physics and a Ph.D. in communications engineering.
