FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for Ü-Tsang, Amdo and Kham Speech Dataset Generation

Yutong Liu, Ziyue Zhang, Ban Ma-bao +7

Tibetan is a low-resource language with minimal parallel speech corpora spanning its three major dialects-Ü-Tsang, Amdo, and Kham-limiting progress in speech modeling. To address…