Showing eess.ASShow all
2 papers · 1 filter
eess.AS2026
Zero-Shot TTS With Enhanced Audio Prompts: Bsc Submission For The 2026 Wildspoof Challenge TTS Track
Jose Giraldo, Alex Peiró-Lilja, Rodolfo Zevallos +1
We evaluate two non-autoregressive architectures, StyleTTS2 and F5-TTS, to address the spontaneous nature of in-the-wild speech. Our models utilize flexible duration modeling to im…
eess.AS2024
Enhancing Crowdsourced Audio for Text-to-Speech Models
José Giraldo, Martí Llopart-Font, Alex Peiró-Lilja +3
High-quality audio data is a critical prerequisite for training robust text-to-speech models, which often limits the use of opportunistic or crowdsourced datasets. This paper prese…