End-to-End Text-to-Speech for Low-Resource Languages by Cross-Lingual Transfer Learning

Citations Over TimeTop 10% of 2019 papers

Abstract

End-to-end text-to-speech (TTS) has shown great success on large quantities of paired text plus speech data.However, laborious data collection remains difficult for at least 95% of the languages over the world, which hinders the development of TTS in different languages.In this paper, we aim to build TTS systems for such low-resource (target) languages where only very limited paired data are available.We show such TTS can be effectively constructed by transferring knowledge from a high-resource (source) language.Since the model trained on source language cannot be directly applied to target language due to input space mismatch, we propose a method to learn a mapping between source and target linguistic symbols.Benefiting from this learned mapping, pronunciation information can be preserved throughout the transferring procedure.Preliminary experiments show that we only need around 15 minutes of paired data to obtain a relatively good TTS system.Furthermore, analytic studies demonstrated that the automatically discovered mapping correlate well with the phonetic expertise.

Related Papers

• → CNN Transfer Learning for Automatic Image-Based Classification of Crop Disease(2018)56 cited
• → Deep Transfer Learning for the Multilabel Classification of Chest X-ray Images(2022)24 cited
• → Performance of True Transfer Learning using CNN DenseNet121 for COVID-19 Detection from Chest X-Ray Images(2021)22 cited
• → COVID-19 detection from chest X-rays using transfer learning with deep convolutional neural networks(2021)7 cited
• → The Diagnosis of COVID-19 Through X-Ray Images via Transfer Learning Pipeline(2021)1 cited