Applying Phonological Features in Multilingual Text-To-Speech
This addresses the challenge of creating more natural and diverse speech synthesis for multilingual applications, but it appears incremental as it builds on existing mapping techniques.
The study tackled the problem of generating native, non-native, and code-switched speech in English and Mandarin using phonological features in text-to-speech systems, and the result proved it feasible as an input system, though further improvements are needed.
This study investigates whether phonological features can be applied in text-to-speech systems to generate native and non-native speech in English and Mandarin. We present a mapping of ARPABET/pinyin to SAMPA/SAMPA-SC and then to phonological features. We tested whether this mapping could lead to the successful generation of native, non-native, and code-switched speech in the two languages. We ran two experiments, one with a small dataset and one with a larger dataset. The results proved that phonological features could be used as a feasible input system, although further investigation is needed to improve model performance. The accented output generated by the TTS models also helps with understanding human second language acquisition processes.