make-a-smart-speaker

The "make-a-smart-speaker" repository offers a comprehensive framework for building an open-source smart speaker, featuring an audio processing pipeline that includes Acoustic Echo Cancellation, Beamforming, and Noise Suppression. It integrates essential components like Keyword Spotting, Speech-to-Text, Natural Language Understanding, and Text-to-Speech, allowing users to create customized voice assistant functionalities. The project encourages collaboration and provides links to additional resources and active initiatives in voice AI development.