Maël Fabien

In this article, I will discuss and summarize the paper: “Social network analysis as a tool for criminal intelligence:understanding its potential from the perspectivesof intelligence analysts” by Morgan Burcher and Chad Whelan.

I have encountered lots of tutorials from 2019 on how to install Spark on MacOS, like this one.

MFCCs have long been the standard hand-crafted features used as inputs for the majority of speech-related tasks.

You might have already heard of Fairseq, a sequence-to-sequence toolkit written in PyTorch by FacebookAI.

I am keeping track here of my Ph.D. process.

In the world, more than 6’000 languages exist, 3’000 of them currently being endangered.

So far, we considered the HMM training under the Maximum Likelihood Estimate (MLE).

When training an ASR system, mismatch can occur between training and test data, due to various sources of variation.

Acoustic modeling allows you to identify phonemes and transitions between them.

So far, we have covered HMM-GMM acoustic modeling and some practical issues related to context and less frequent phonemes.