Learning pronunciation from a foreign language in speech synthesis networks

TL;DR

This paper investigates how multilingual speech synthesis networks learn phoneme pronunciations across languages, demonstrating that phoneme embeddings cluster by similarity and enabling cross-language synthesis and transfer learning.

Contribution

It introduces a framework for multilingual speech synthesis that leverages cross-language phoneme relations and improves low-resource language synthesis through pre-training and fine-tuning.

Findings

Phoneme embeddings cluster by pronunciation similarity across languages.

Networks can synthesize speech in a language using data from another language.

Pre-training on multiple languages enhances low-resource language synthesis.

Abstract

Although there are more than 6,500 languages in the world, the pronunciations of many phonemes sound similar across the languages. When people learn a foreign language, their pronunciation often reflects their native language's characteristics. This motivates us to investigate how the speech synthesis network learns the pronunciation from datasets from different languages. In this study, we are interested in analyzing and taking advantage of multilingual speech synthesis network. First, we train the speech synthesis network bilingually in English and Korean and analyze how the network learns the relations of phoneme pronunciation between the languages. Our experimental result shows that the learned phoneme embedding vectors are located closer if their pronunciations are similar across the languages. Consequently, the trained networks can synthesize the English speakers' Korean speech and vice versa. Using this result, we propose a training framework to utilize information from a different language. To be specific, we pre-train a speech synthesis network using datasets from both high-resource language and low-resource language, then we fine-tune the network using the low-resource language dataset. Finally, we conducted more simulations on 10 different languages to show it is generally extendable to other languages.