[Paper] SUPERB: Speech processing Universal PERformance Benchmark

elf-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB).

Read More

British intelligence agency GCHQ publishes ‘Ethics of AI’ report

GCHQ AI ethics report

The intelligence agency’s first-ever public report details how AI can be used “ethically” for cyber operations. GCHQ (Government Communications Headquarters) is tasked with providing signals intelligence and information assurance to the government and armed forces of the United Kingdom and its allies. Jeremy Fleming, Director of GCHQ, said: “We need honest, mature conversations about the […]

Read More

AI helps patients to get more rest while reducing staff workload

A team from Feinstein Institutes for Research thinks AI could be key to helping patients get more rest while reducing the burden on healthcare staff. Everyone knows how important adequate sleep is for recovery. However, patients in pain – or just insomniacs like me – can struggle to get the sleep they need. “Rest is…

Read More

Microsoft’s new AI auto-captions images for the visually impaired

A new AI from Microsoft aims to automatically caption images in documents and emails so that software for visual impairments can read it out. Researchers from Microsoft explained their machine learning model in a paper on preprint repository arXiv. The model uses VIsual VOcabulary pre-training (VIVO) which leverages large amounts of paired image-tag data to…

Read More

List of inverse Reinforcement Learning (IRL) papers

inverse Reinforcement Learning (IRL) papers

Inverse Reinforcement Learning papers: A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models. (IRL, Algorithms, Apprenticeship Learning, Maximum Margin Planning, Maximum Entropy, Nonlinear with Gaussian Processes, Generative Adversarial Imitation Learning).

Read More