Voice cloning with Italian phonetics

Astolfi, Federico (A.A. 2020/2021) Voice cloning with Italian phonetics. Tesi di Laurea in Artificial intelligence and machine learning, Luiss Guido Carli, relatore Marco Querini, pp. 44. [Bachelor's Degree Thesis]

PDF (Full text)
Download (2MB) | Preview


State of the art. WaveNet. Tacotron. Generalized end-to-end loss for speaker verification (GE2E). Speaker verification to multispeaker text-to-speech. The training process. Mel-spectrogram. Lamda labs–cloud GPUs. The encoder. LSTM (long short-term memory) model. The encoder structure. Data. The model. UMAP. Preprocess. The training. The synthesizer. Preprocess. The training. The Vocoder. Streamlit implementation.


Bibliografia: pp. 41-44.

Thesis Type: Bachelor's Degree Thesis
Institution: Luiss Guido Carli
Degree Program: Bachelor's Degree Programs > Bachelor's Degree Program in Management and Computer Science, English language (L-18)
Chair: Artificial intelligence and machine learning
Thesis Supervisor: Querini, Marco
Academic Year: 2020/2021
Session: Autumn
Deposited by: Alessandro Perfetti
Date Deposited: 29 Mar 2022 10:05
Last Modified: 29 Mar 2022 10:05
URI: https://tesi.luiss.it/id/eprint/31866


Downloads per month over past year

Repository Staff Only

View Item View Item