WaveNet Turns 10: Author Traces Speech Synthesis from Waveforms to Multimodal LLMs
heiga_zen · x · 2026-09-09
Google speech researcher Heiga Zen marks the 10th anniversary of WaveNet, whose raw-waveform generation paradigm replaced concatenative and statistical parametric TTS in 2016.
The decade in review:
- Encoder-decoder models like Tacotron enabled end-to-end text-to-acoustics
- VITS and NaturalSpeech generated waveforms directly without intermediate representations
- AudioLM and VALL-E tokenized speech into LLM frameworks via SoundStream
- Multimodal LLMs like Gemini now seamlessly fuse modalities for natural dialogue
He predicts the next decade: finer emotion/context modeling, ultra-low-latency conversation, and robot integration.
More from Multimodal
- Magnific teases October 28 release: 'We're making it move' — cuenca · 2026-10-27
- Midjourney --sref demo: retro Americana Batman art series — gizakdag · 2026-10-27
- AI video is a new medium, not cinema or animation — and it's perfect for depicting dreams — Kyrannio · 2026-10-27
- Dad turns his toddler's 31-year-old quote into a song via SUNO kids' choir — NathanpmYoung · 2026-10-27
- Band's local-AI music video hits 200k views: 900 generations kept 64, 3-second clips beat face drift — Hwang0500 · 2026-10-27
- Adobe Firefly video editor walkthrough: one-sentence Quick Cut turns 32s into 20s — LudovicCreator · 2026-10-26