2021 Call for Code Awards: Live from New York, with SNL’s Colin Jost! Learn more

IBM Developer Blog

Follow the latest happenings with IBM Developer and stay in the know.

Develop an acoustic model by using a few curl commands


Ever wanted to create your own personalized artificial intelligence (AI) bot to identify whatever you say to it? You probably must have at some point, but you might have dropped the idea because either it’s too complex or time-consuming to train it or create it. In this blog, I’ll explain how you can create your own custom speech models using IBM® Watson™. The best part is that you don’t have to write a single line of code for this.

The blog summarizes the steps to create an acoustic model by using a few curl commands along with a data set that includes accented speakers and audio files with background noise. It also shows how easy it is to create a language model by using a corpus file containing domain-specific terms.

Be sure to read it if you are interested in speech recognition and want to create custom models for clients such as the oil & gas industry.