WaveNet | DeepMind
We research and build safe AI systems that learn how to solve problems and advance scientific discovery for all. Explore our work: deepmind.com/research
Research Introduced in 2016, WaveNet was one of the first AI models to generate natural-sounding speech. Since then, it has inspired research, products, and applications in Google — and beyond. The challenge Learning from human speech Rapid advances The power of voice Widespread legacy The challenge For decades, computer scientists tried reproducing the nuances of the human voice to make computer-generated voices more natural. Most text-to-speech systems relied on “concatenative synthesis” — a pain-staking process of cutting voice recordings into phonetic sounds and recombining them…
saved by
related reading
- Crossing the uncanny valley of conversational voice | Sesamesesame.com
- Understanding WaveNet architecturemedium.com
- What Is ChatGPT Doing … and Why Does It Work?-Stephen Wolfram Writingswritings.stephenwolfram.com
- Generating music in the waveform domain – Sander Dielemansander.ai
- WaveGrad: Estimating Gradients for Waveform Generationarxiv.org
- Free AI Voice Generator & Voice Agents Platform | ElevenLabselevenlabs.io
- Silent speech with ultrasound — Alephalephneuro.com
- Replicate - Run AI with an APIreplicate.com
- GANSynth: Making music with GANsmagenta.tensorflow.org
- Voice AI & Voice Agents | An Illustrated Primervoiceaiandvoiceagents.com
- The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io
- Woosh: A Sound Effects Foundation Modelarxiv.org