Learning pronunciation from a foreign language in speech synthesis networks
This work addresses the challenge of limited data for speech synthesis in low-resource languages, offering a practical method to improve performance, though it is incremental as it builds on existing multilingual training approaches.
The study tackled the problem of leveraging multilingual data to improve speech synthesis for low-resource languages by analyzing how networks learn pronunciation similarities across languages, resulting in a training framework that uses high-resource language data to enhance synthesis quality for low-resource languages, with experiments showing applicability across 10 languages.
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.