Neural Vocoding for Singing and Speaking Voices with the Multi-Band Excited WaveNet
The use of the mel spectrogram as a signal parameterization for voice generation is quite recent and linked to the development of neural vocoders. These are deep neural networks that allow reconstructing high-quality speech from a given mel spectrogram. While initially developed for speech synthesis...
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Artigo |
| Lingua: | Inglês |
| Pubblicazione: |
MDPI AG
2022-02-01
|
| Serie: | Information |
| Soggetti: | |
| Accesso online: | https://www.mdpi.com/2078-2489/13/3/103 |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|