What can curated pronunciation data do for text-to-speech models?
Watch the recording
Do you want to learn more about AI voice generation?
On 18 July 2024, we sat down with WellSaid to discuss how human-curated data can support innovative text-to-speech advancements by helping tackle the complexities of AI voice generation and give content creators more control over their voiceover preferences.
Here’s what you’ll discover:
- WellSaid’s pioneering AI voice generation
- Oxford Languages’ human-curated pronunciation data
- Linguistic challenges in text-to-speech
- Novel respelling systems
Meet the speakers
Rhyan Johnson | Machine Learning Product Manager and Staff Engineer, WellSaid
Rhyan is Machine Learning Product Manager and Staff Data Engineer at WellSaid, developing AI text-to-speech services and features used by the companies spanning the tech ecosystem. Previously, Rhyan worked as a Software Development Engineer at Amazon, enhancing conversational interactions with Alexa and at The MITRE Corporation, advancing aviation and air traffic control safety in partnership with the Federal Aviation Administration and the Civil Aviation Authority of Singapore. She also co-founded Freely Collective, a venture offering art and design services to help combat human trafficking.
Dr. Catherine Sangster | Executive Editor: Pronunciations, Oxford Languages
Catherine is our Executive Editor of Pronunciations. Before moving into lexicography, she headed the BBC Pronunciation Unit, and completed a D.Phil. in Sociophonetics.
Dr. Holly Dann (Moderator) | Editor: Pronunciations, Oxford Languages
Holly has been working as a pronunciation lexicographer with us since 2022. Before coming to Oxford Languages, she completed a PhD in sociophonetics at the University of Sheffield, and worked as a postdoctoral Research Associate on the Manchester Voices project.
Sign up for future updates
Stay informed with future webinars and events when you subscribe to our mailing list.