Adaptive Recognition with Layered Optimization

TonyB Speaking 'ARLO'


ARLO was developed for classifying bird calls and using visualizations to help scholars classify pollen grains. ARLO has the ability to extract basic prosodic features such as pitch, rhythm and timbre for discovery (clustering) and automated classification (prediction or supervised learning), as well as visualizations. The current implementation of ARLO for modeling runs in parallel on systems at the Texas Advanced Computing Center (TACC) on the Stampede supercomputer.

Open Source

ARLO is open-source, meaning you are free to use or modify it, whether for yourself or to contribute back to the community. The ARLO source code repositories are available on Bitbucket

We are always on the lookout for additional help. See Contributing for more information.


ARLO Documentation is available at

Additionally, the HiPSTAS group, an organization of users focused around ARLO and similar technologies, maintains further documentation at



ARLO's backend handles the heavy-lifting - modeling, searching, classification and so on. The backend is specifically designed to enable numerous machines to split up large tasks, when one machine just can't cope.

Web Interface

Users interact with ARLO through a web browser, meaning there is no software to install to individual's machines. We don't even use client side Flash or Java.


A RESTful API allows users to script additional tools, automate tasks, and embed ARLOs methods in other tools.

Hosted Service

A freely hosted version is currently available for a limited number of users, though we are pretty much at capacity given our current resources. However, if you would like to contribute resources or setup your own installation, let us know and we'll see how we can help.