Advancing Voice Cloning for Nepali: Leveraging Transfer Learning in a Low-Resource Language

TL;DR

This paper presents a transfer learning approach to improve voice cloning for Nepali, a low-resource language, enhancing audio quality and speaker similarity with limited data.

Contribution

It introduces a transfer learning-based voice cloning system tailored for Nepali, addressing data scarcity and quality issues in low-resource language speech synthesis.

Findings

Effective transfer learning improved Nepali voice cloning quality.

The system achieved natural-sounding Nepali speech with limited data.

Enhanced speaker similarity and reduced audio artifacts.

Abstract

Voice cloning is a prominent feature in personalized speech interfaces. A neural vocal cloning system can mimic someone's voice using just a few audio samples. Both speaker encoding and speaker adaptation are topics of research in the field of voice cloning. Speaker adaptation relies on fine-tuning a multi-speaker generative model, which involves training a separate model to infer a new speaker embedding used for speaker encoding. Both methods can achieve excellent performance, even with a small number of cloning audios, in terms of the speech's naturalness and similarity to the original speaker. Speaker encoding approaches are more appropriate for low-resource deployment since they require significantly less memory and have a faster cloning time than speaker adaption, which can offer slightly greater naturalness and similarity. The main goal is to create a vocal cloning system that produces audio output with a Nepali accent or that sounds like Nepali. For the further advancement of TTS, the idea of transfer learning was effectively used to address several issues that were encountered in the development of this system, including the poor audio quality and the lack of available data.