An emerging trend in AI is the availability of technologies that add speech capabilities by enabling fast and accurate speech transcription in multiple languages for various use cases, including but not limited to customer self-service, agent assistance and speech analytics. This course takes the learners through applying IBM Watson Speech to Text and Text to Speech technology for their unique use case. The course starts by explaining at a high level some common business use cases for Watson Speech Services and the underlying science behind the technology of Watson Speech to Text and Text to Speech as developed by IBM, leverage the API methods for calling Speech services, customize, and deploy speech prototypes to suit your unique domain language and finally the course will end by integrating voice capabilities to an existing agent Watson Assistant using Watson Speech to Text and Text to Speech.
Before taking this course, you should have:
The following services within the IBM Cloud are extensively used for this course. Prior setup is recommended. This setup is not mandatory, as a detailed walk-through of creating instances and accessing the following services are covered in the course.
After completing this course, you should be able to:
Module 1
Module 2
Module 3
Module 4
Join our public courses in our Norway facilities. Private class trainings will be organized at the location of your preference, according to your schedule.