John HughesHow to Boost Emotion Recognition Performance in Speech Using Contrastive Predictive CodingUsing Contrastive Predictive Coding to significantly improve the relative reduction in error by 30% for a speech emotion recognition…Sep 2, 20202Sep 2, 20202
MichaeltansinispeechmaticsHow to optimise automatic speech recognition performance using MKLThis article covers how Speechmatics continues to optimize our ASR performance with the Intel MKL software library.Aug 12, 2020Aug 12, 2020
David MacLeodHow to Build a Streaming DataLoader with PyTorchLearn how the new PyTorch 1.2 dataset class `torch.utils.data.IterableDataset` can be used to implement a parallel streaming DataLoader.Oct 31, 201914Oct 31, 201914
Will WilliamsHow to Deploy Machine Learning in ProductionHints and tips on how you can help your business deploy machine learning into production so that you and your customers can consume it…Aug 15, 20191Aug 15, 20191
Eric HendersonHow to Evaluate Speech Technology Providers — 4 Key ConsiderationsEvaluating speech technology providers can be difficult and frustrating. What do you measure? How do you measure it? Often the unit of…Jul 17, 2019Jul 17, 2019
Tom AshHow to make the most of machine learning — what is it and how can we use it?An entry-level introduction to machine learning addressing what machine learning is, why we use it, what it can do, and how we can train…May 30, 2019May 30, 2019
James DobsonWhat do DevOps and Machine Learning Have in Common?• Data storage/Manipulation • Orchestration • Scaling • Packaging All these things are in traditional microservices…May 16, 2019May 16, 2019
Anartz NuinHow to write Kubernetes custom controllers in GoThis article will provide an introduction on how to write Kubernetes custom controllers using the official API client library…Mar 28, 20191Mar 28, 20191
Tom AshHow to make the most of data surplus — domain adaptationIt may be that your large amounts of data are just not the type of data you think you need. Don’t despair!Mar 21, 2019Mar 21, 2019
Tom AshHow to make the most of data surplus — filter out rubbishThe truth is that a lot of your data is probably bad data. That is not your fault. You did your best.Mar 14, 2019Mar 14, 2019