Empowering Global Voices: A Data-Efficient, Phoneme-Tone Adaptive Approach to High-Fidelity Speech Synthesis
This work addresses the problem of multilingual accessibility for under-resourced languages, offering a scalable solution for data-limited TTS production, though it appears incremental as it builds on existing frameworks.
The paper tackles the challenge of building high-quality text-to-speech systems for under-resourced languages with limited data and linguistic complexities, achieving state-of-the-art performance as confirmed by extensive evaluations. It demonstrates effectiveness using Thai as a case study, enabling zero-shot voice cloning and improved performance across diverse applications like finance and healthcare.
Text-to-speech (TTS) technology has achieved impressive results for widely spoken languages, yet many under-resourced languages remain challenged by limited data and linguistic complexities. In this paper, we present a novel methodology that integrates a data-optimized framework with an advanced acoustic model to build high-quality TTS systems for low-resource scenarios. We demonstrate the effectiveness of our approach using Thai as an illustrative case, where intricate phonetic rules and sparse resources are effectively addressed. Our method enables zero-shot voice cloning and improved performance across diverse client applications, ranging from finance to healthcare, education, and law. Extensive evaluations - both subjective and objective - confirm that our model meets state-of-the-art standards, offering a scalable solution for TTS production in data-limited settings, with significant implications for broader industry adoption and multilingual accessibility.