Robot Voices in Multimedia: Adventures in Text-to-speech

Home/Robot Voices in Multimedia: Adventures in Text-to-speech
Robot Voices in Multimedia: Adventures in Text-to-speech
Track: Technical | T5 |   Everyone |
Friday, November 8, 2019, 9:30am – 10:15am
Held in: Atherton
Presenter:
Gilbert Segura - Compass Languages
Host: Gary Lefman

Text-to-speech (TTS) has been around for ages — but just like machine translation, this technology is different and better in the 21st century. In this session we will cover the methods and advantages of TTS and how other tools such as speech recognition and neural machine translation can all work together.

Takeaways: Attendees will hear about the current TTS landscape (Google, Polly, Azure), see examples of TTS capabilities — and its limitations and learn where TTS is useful and where it is not recommended.

Secured By miniOrange