0

Arabic TTS with FastPitch: Reproducible Baselines, Adversarial Training, and Oversmoothing Analysis

Reproducible Arabic TTS baselines using FastPitch with cepstral-domain metrics and adversarial spectrogram loss improve prosodic diversity and reduce oversmoothing.

Year
2025
Venue
arXiv 2025
Authors
1
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2512.00937ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Arabic text-to-speech (TTS) remains challenging due to limited resources and complex phonological patterns. We present reproducible baselines for Arabic TTS built on the FastPitch architecture and introduce cepstral-domain metrics for analyzing oversmoothing in mel-spectrogram prediction. While traditional Lp reconstruction losses yield smooth but over-averaged outputs, the proposed metrics reveal their temporal and spectral effects throughout training. To address this, we incorporate a lightweight adversarial spectrogram loss, which trains stably and substantially reduces oversmoothing. We further explore multi-speaker Arabic TTS by augmenting FastPitch with synthetic voices generated using XTTSv2, resulting in improved prosodic diversity without loss of stability. The code, pretrained models, and training recipes are publicly available at: https://github.com/nipponjo/tts-arabic-pytorch.

Authors

1