Pixel-TTS: Image based Text Rendering for Robust Text-to-Speech 文章

ArXiv CS.CV2026-06-16NEWSen作者: Adarsh Arigala, Arjun Gangwar, S Umesh, Yova Kementchedjhieva

查看原文 →

Pixel-TTS: Image based Text Rendering for Robust Text-to-Speech · 相关技术

相关技术

visually grounded speech synthesis embedding matrix expansion embedding expansion zero-shot cross-lingual adaptation Unicode encodings pixel-based text modeling 2D convolutional layer Unicode