AI engineering glossary · Generative media multimodal
What is tacotron?
Tacotron: A family of sequence-to-sequence text-to-speech models that use attention to predict mel spectrograms directly from characters or phonemes, which are then converted to audio by a vocoder. It showed that end-to-end TTS could be natural.
Tacotron: an example
Given the letters of a sentence, Tacotron outputs mel spectrogram frames that a vocoder turns into speech.
Related terms
More Generative media multimodal terms
- Temporal consistency
- Text-to-3D generation
- Text-to-image generation
- Text-to-speech
- Text-to-video generation
- Textual inversion
- Variational autoencoder
- Video generation
Where you learn it
Tacotron is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.