An Empirical Study on L2 Accents of Cross-lingual Text-to-Speech Systems via Vowel Space

TL;DR

This study uses vowel space analysis to evaluate L2 accents in cross-lingual TTS systems, revealing differences based on architecture and linguistic features, and highlighting the importance of language-specific handling.

Contribution

It introduces vowel space analysis as an effective tool to assess L2 accents in cross-lingual TTS, providing insights into architectural and linguistic factors affecting accent quality.

Findings

Glow-TTS is less accented than Tacotron.

Non-shared vowels exhibit stronger L2 accents.

L2 accents in TTS resemble those of human L2 learners.

Abstract

With the recent developments in cross-lingual Text-to-Speech (TTS) systems, L2 (second-language, or foreign) accent problems arise. Moreover, running a subjective evaluation for such cross-lingual TTS systems is troublesome. The vowel space analysis, which is often utilized to explore various aspects of language including L2 accents, is a great alternative analysis tool. In this study, we apply the vowel space analysis method to explore L2 accents of cross-lingual TTS systems. Through the vowel space analysis, we observe the three followings: a) a parallel architecture (Glow-TTS) is less L2-accented than an auto-regressive one (Tacotron); b) L2 accents are more dominant in non-shared vowels in a language pair; and c) L2 accents of cross-lingual TTS systems share some phenomena with those of human L2 learners. Our findings imply that it is necessary for TTS systems to handle each language pair differently, depending on their linguistic characteristics such as non-shared vowels. They also hint that we can further incorporate linguistics knowledge in developing cross-lingual TTS systems.