ELEC-C5220 - Koneoppiminen informaatioteknologiassa, Luento-opetus, 11.1.2024-25.4.2024
This course space end date is set to 25.04.2024 Search Courses: ELEC-C5220
Lecture 9: Speech Synthesis
Krav för slutförande
Luentokalvot saatavilla täällä.
--
Lecture slides available here.
Voice cloning example video we watched in the lecture: .
--
Reading list:
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
Paper: https://arxiv.org/abs/1712.05884
Demo:https://google.github.io/tacotron/publications/tacotron2/
Code: https://github.com/NVIDIA/tacotron2
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Paper: https://arxiv.org/abs/2010.05646
Demo: https://jik876.github.io/hifi-gan-demo/
Code: https://github.com/jik876/hifi-gan
Senast redigerad: måndag, 18 mars 2024, 12:49