Digests » 175

sponsor

The #1 Rated API for Speech-to-Text

Automatically transcribe audio and video files with human-level accuracy. Voted the Best Public API of 2020 and funded by Y Combinator - AssemblyAI's Speech-to-Text API is used by both Fortune 500 companies and developers around the world. Accurately convert speech to text by applying AssemblyAI's powerful deep learning models with an easy-to-use API.

this week's favorite

What is an A/B Test?

This post has focused on building intuition: the basics of an A/B test, why it’s important to run an A/B test versus rolling out a feature and looking at metrics pre- and post- making a change, and how we turn an idea into a testable hypothesis.

Measuring semantic changes using temporal word embedding

A guide to how temporal word embeddings can be used to measure word evolution and some considerations regarding stability of embedding methods.

Decoupling magnitude and phase estimation with Deep ResUNet for music source separation

Deep neural network based methods have been successfully applied to music source separation. They typically learn a mapping from a mixture spectrogram to a set of source spectrograms, all with magnitudes only. This approach has several limitations: 1) its incorrect phase reconstruction degrades the performance, 2) it limits the magnitude of masks between 0 and 1 while we observe that 22% of time-frequency bins have ideal ratio mask values of over~1 in a popular dataset, MUSDB18, 3) its potential on very deep architectures is under-explored.

Real-world evidence and the path from data to impact

When an acute crisis strikes, it creates an urgency to help real people, right now. However, not all crises are acute, and not all forms of response deliver direct assistance. While we need to attend to foreground crises like floods, fire, and famine, we also need to pay attention to the background crises that precipitate them—for many, the background crisis is already the foreground of their lives.

Summarizing books with human feedback

Scaling human oversight of AI systems for tasks that are difficult to evaluate.