The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech
2023
Online
report
We compare phone labels and articulatory features as input for cross-lingual transfer learning in text-to-speech (TTS) for low-resource languages (LRLs). Experiments with FastSpeech 2 and the LRL West Frisian show that using articulatory features outperformed using phone labels in both intelligibility and naturalness. For LRLs without pronunciation dictionaries, we propose two novel approaches: a) using a massively multilingual model to convert grapheme-to-phone (G2P) in both training and synthesizing, and b) using a universal phone recognizer to create a makeshift dictionary. Results show that the G2P approach performs largely on par with using a ground-truth dictionary and the phone recognition approach, while performing generally worse, remains a viable option for LRLs less suitable for the G2P approach. Within each approach, using articulatory features as input outperforms using phone labels.
Comment: Accepted at INTERSPEECH 2023
Titel: |
The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech
|
---|---|
Autor/in / Beteiligte Person: | Do, Phat ; Coler, Matt ; Dijkstra, Jelske ; Klabbers, Esther |
Link: | |
Veröffentlichung: | 2023 |
Medientyp: | report |
Schlagwort: |
|
Sonstiges: |
|