Personalized Speech Enhancement: Data- and Resource-Efficient Machine Learning

Explore personalized speech enhancement techniques in this lecture by Minje Kim from the Center for Language & Speech Processing at JHU. Dive into data- and resource-efficient machine learning approaches for improving individual user experiences. Learn about the challenges of training personalized models with limited user data and the potential of self-supervised learning. Discover modularized speech enhancement models that require minimal test-time user data while achieving personalization goals. Gain insights into creating computationally efficient AI solutions for resource-constrained devices, making artificial intelligence more accessible and affordable for society.