Voice Cloning Using Transfer Learning with Audio Samples
UMT Artificial Intelligence Review · 2023
DOI: 10.32350/umt-air.32.04 ↗Kurz gefasst
Fachartikel in der Zeitschrift UMT Artificial Intelligence Review, 2023. Verfasst von Usman Nawaz und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Voice cloning refers to the artificial replication of a certain human voice. Several deep learning approaches were studied for voice cloning. After studying learning approaches, a cloning system was offered that creates natural-sounding audio samples within few seconds of source speech from the target speaker. From a speaker verification challenge to text-to-speech synthesis with multi-speaker capability, the current study used a transfer learning technique. In a zero-shot mode, this system creates speech sounds in the voices of various speakers, even individuals who were not seen during the training process. The current study used latent embedding’s to encode speaker-specific information, enabling additional model parameters to be pooled across all speakers. The speaker modelling stage was separated from voice synthesis by training a discrete speaker-discriminative encoder network. This is because networks require distinct types of input, disconnection enables each to be trained using separate datasets. When employed for zero-shot adaptability to unknown speakers, an embedding-based technique for voice cloning enhances speaker resemblance. Furthermore, it reduces computational resource needs which may be advantageous for use-cases requiring minimal resource deployment.
Zitieren
APA
Nawaz, U., Raza, U. A., Farooq, A., Iqbal, M. J., & Tariq, A. (2023). Voice Cloning Using Transfer Learning with Audio Samples. UMT Artificial Intelligence Review. https://doi.org/10.32350/umt-air.32.04
Vancouver
Nawaz U, Raza UA, Farooq A, Iqbal MJ, Tariq A. Voice Cloning Using Transfer Learning with Audio Samples. UMT Artificial Intelligence Review. 2023. doi:10.32350/umt-air.32.04
BibTeX
@article{Nawaz2023,
author = {Nawaz, Usman and Raza, Usman Ahmed and Farooq, Amjad and Iqbal, Muhammad Junaid and Tariq, Ammara},
title = {Voice Cloning Using Transfer Learning with Audio Samples},
journal = {UMT Artificial Intelligence Review},
year = {2023},
doi = {10.32350/umt-air.32.04}
}
EUVIMED