Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the latest advancements in Speech to Text and Text to Speech technologies in this 27-minute AI Show episode featuring Edward Un and Heiko Rahmel. Dive into core scenarios for Speech services, including call center transcription, content creation, read-out functionality, and chatbots. Watch demonstrations of Speech to Text capabilities and pronunciation assessment tools. Discover new Text to Speech features, including cross-lingual adaptation and custom voice options. Learn about the ethical considerations surrounding Custom Neural Voice technology. Gain insights into real-world applications for both Speech to Text and Text to Speech. Access additional resources and quickstart guides to implement these technologies in your own projects.
Syllabus
AI Show begins.
Seth welcomes Edward and Heiko.
Speech to Text - What's new.
Demo - Speech to Text.
Pronunciation Assessment.
Text to Speech - What's new.
Cross Lingual Adaptation - Explore voice options.
Demo - Custom voice .
Ethics of Custom Neural Voice.
Real-world uses: Speech to Text.
Real-world uses: Text to Speech.
Learn more.
Taught by
Microsoft Developer