Machine learning in the cloud

13 June, 2016

 - credit:

Edward has been invited to talk at a Catalyst Cloud breakfast about how Dragonfly’s Kōkako technology makes use of the cloud computing platform. Kōkako uses machine learning to monitor the proportion of Māori language broadcast on New Zealand’s iwi radio stations.

“Every hour, we receive the iwi radio audio files as they are archived by Ngā Taonga,” says Edward. “The audio files are large, and it’s a real advantage that they can be processed in Wellington rather than going to an international provider – faster and significantly cheaper.”

Edward says Catalyst’s infrastructure also makes it easy to host the intensive computation tasks that Kōkako relies on. Kōkako uses a database server, the cloud object-store, and containerised micro-services to process the data. We trained the machine learning algorithm to distinguish spoken Māori from English, and the trained algorithm is run over new audio as it arrives.

“We use the Catalyst Cloud to keep our servers running online 24-7, so our clients always have access to up to date reporting. We have full control over the servers, but Catalyst looks after all the backups and maintenance. This makes running Kōkako relatively simple – using the cloud removes a whole layer of responsibility from us.”

The breakfast event features two other speakers, also talking about the Catalyst Cloud.

“It’s nice to be able to tell our story. Machine learning is developing rapidly at the moment, and this is a relatively sophisticated application that’s already up and running.”

Edward also sees plenty of opportunities for the technology to develop in new areas, such as classifying streaming video.

“We’re especially interested in the development of video monitoring in fisheries and whether there are opportunities to help with processing the hours and hours of footage that gets recorded.”

Read more about Kōkako, developed by Dragonfly for Te Māngai Pāho.

The Catalyst Cloud breakfast will be held in Auckland on 22 June, beginning at 7:30. All are welcome to come along to learn more about the Catalyst Cloud.