Kaydedildi:
| Asıl Yazarlar: | , , |
|---|---|
| Materyal Türü: | Preprint |
| Baskı/Yayın Bilgisi: |
2022
|
| Konular: | |
| Online Erişim: | https://arxiv.org/abs/2210.17153 |
| Etiketler: |
Etiketle
Etiket eklenmemiş, İlk siz ekleyin!
|
İçindekiler:
- End-to-end (E2E) systems synthesise high-quality speech, but this typically requires a large amount of data. As E2E synthesis progressed from Tacotron to FastSpeech2, it became evident that features representing prosody, particularly sub-word durations, are important for error-free synthesis. Variants of FastSpeech use a teacher model or forced alignments for training. This paper uses signal processing cues in tandem with forced alignment to produce accurate phone boundaries for the training data. As a result of better duration modelling, good-quality synthesisers are developed. Evaluations indicate that systems developed using the proposed signal processing-aided approach are better than systems developed using other alignment approaches, especially in low-resource scenarios. Our systems also outperform the existing best TTS systems available for 13 Indian languages.