How a Neural Network Learns to Talk in 14 Minutes [Video]

Night mode

During some research on machine learning and neural networks, I came across one really cool video by SomethingUnreal. In this clip of roughly 14 minutes, you can see how a neural network attempts to generate English speech based on raw waveform training data. A lot of gibberish happens along the way but the results are highly fascinating. What do you think?


YouTube: Neural Network Tries to Generate English Speech (RNN/LSTM)

Photo credit: Surian Soosay

Christopher Isak

Christopher Isak

Managing Editor at TechAcute
Hi there and thanks for reading my article! I'm Chris. I write about technology news and share experiences from my life in the enterprise world. I love readers who leave a comment. 😉
Christopher Isak

@ChristopherIsak

Tech Journalist ✖ @TechAcuteCom Founder and Managing Editor ✖ Gamer ✖ Covering Collaboration, Games, AI, VR, AR, FinTech, Design, UX, VC, Startups ✖ 求是创新 ✖ 爱茶
Been about 90 min. in the @msexcel #Android app today. Believe it or not but they improved it so much that you can… https://t.co/XHvB56gn4i - 3 hours ago
Christopher Isak
Christopher Isak

Latest posts by Christopher Isak (see all)

Christopher Isak

Hi there and thanks for reading my article! I'm Chris. I write about technology news and share experiences from my life in the enterprise world. I love readers who leave a comment. ;)

Leave a Reply