Lanfrica Talks #9 | Adversarial Text-to-Speech for low-resource languages by Ashraf Hatim Elneima

Lanfrica Talks
10/10/2022 21 min
Lanfrica Talks #9 | Adversarial Text-to-Speech for low-resource languages by Ashraf Hatim Elneima

Listen "Lanfrica Talks #9 | Adversarial Text-to-Speech for low-resource languages by Ashraf Hatim Elneima"

Descargar episodio

Episode Synopsis

Even though there is a data shortage for African languages, it is still possible to create effective speech models for them. Learn how to improve voice synthesis models for low-resource languages by utilizing the high-frequency similarities between languages.--- Send in a voice message: https://podcasters.spotify.com/pod/show/lanfrica-talks-podcast/message

More episodes of the podcast Lanfrica Talks

Josephine Zingani - Empowering Women: The Impact of Bwalo Lathu Collective and the Role of Native Languages in Knowledge Sharing 19/08/2024
Alexander Visheratin | How a passion project became the state of the art in text and image retrieval 21/05/2024
Zainab Abdullahi - Tuberculosis in Africa | Lanfrica Talks 24/03/2024
Kathryn Kure & Jonathan Poritz - Will "AInt" DDOS The Commons? 13/03/2024
Chisom Paula Ogamba: the Sapir-Whorf Hypothesis, language habits, sexual abuse, social media, “chi” / God, spiritual entities and pastors 27/01/2024
Brian Muhia: the struggles of finding your path, mechanistic interpretability, causality, Fahamu 14/12/2023
Opeyemi Osakuade: To what extent do speech models capture the tones of tonal languages? 01/12/2023
Why should we care about AI and healthcare in Africa? 14/11/2023
Elizabeth Salesky: The Caffeinated Optimist 30/10/2023
From Google Summer of Code to Future AI Engineer: Favour James' Journey 17/10/2023
© 2003-2025 ZARZA | AHEAD OF OUR TIME
privacy policy
In God we trust In God we trust
PreSales Questions? Click Here
or call our toll-free line at +1-888-5002068 Miami, Florida, USA