ELEC-C5220 - Koneoppiminen informaatioteknologiassa, Luento-opetus, 11.1.2024-25.4.2024

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