These Facebook Projects Brings Self-Supervised Learning To Speech Analysis
Three new open source projects that showed a lot of promise to reduce the dependencies on labeled datasets for speech recognition systems.
I recently started an AI-focused educational newsletter, that already has over 65,000 subscribers. TheSequence is a no-BS (meaning no hype, no news etc) ML-oriented newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers and concepts. Please give it a try by subscribing below:
Speech is the cornerstone of human communication and one of the clearest expression of our superior intelligence compared to other species. Not surprisingly, speech has been one of the core areas of focus on the recent wave of artificial intelligence(AI) systems. Automatic speech recognition(ASR) systems have been one of the most active areas of AI research and development producing remarkable breakthroughs like digital assistants or video analysis solutions…
