Amazon Transcribe is now available in Asia Pacific (Seoul) and EU (Frankfurt) with added language support for Spanish (ES)

Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for you to add speech-to-text capabilities to your applications. Starting today, Amazon Transcribe becomes available in two new AWS regions, Asia Pacific (Seoul) and EU (Frankfurt). Additionally, new language support for Spanish (ES) is now available in all regions where Amazon Transcribe is available.

Amazon Comprehend Now Supports Confusion Matrices for Custom Classification

Amazon Comprehend helps you solve a variety of use cases with custom classification. For example, you can build classifiers to organize your daily customer feedback into categories like “loyalty”, “sales” or “product defect”. Amazon Comprehend removes the complexity to create custom classification models, requiring only a CSV file with labels and example text. A confusion matrix helps you understand how your labels are performing based on the training data you provided. For example, if you have two labels with similar training content, the custom classification model may not be able to clearly distinguish between these labels. Using the confusion matrix, you can focus on creating better training content, so each label is more distinct from the other.
Get started with Amazon Comprehend custom classification models here and learn more about how to use a confusion matrix as part of training your model here.