BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

no code implementations • 12 Feb 2024 • Mateusz Łajszczak, Guillermo Cámbara, Yang Li, Fatih Beyhan, Arent van Korlaar, Fan Yang, Arnaud Joly, Álvaro Martín-Cortinas, Ammar Abbas, Adam Michalski, Alexis Moinet, Sri Karlapati, Ewa Muszyńska, Haohan Guo, Bartosz Putrycz, Soledad López Gambino, Kayeon Yoo, Elena Sokolova, Thomas Drugman

Echoing the widely-reported "emergent abilities" of large language models when trained on increasing volume of data, we show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences.

Disentanglement

Enhancing the Stability of LLM-based Speech Generation Systems through Self-Supervised Representations

no code implementations • 5 Feb 2024 • Álvaro Martín-Cortinas, Daniel Sáez-Trigueros, Iván Vallés-Pérez, Biel Tura-Vecino, Piotr Biliński, Mateusz Lajszczak, Grzegorz Beringer, Roberto Barra-Chicote, Jaime Lorenzo-Trueba

Using speaker-disentangled codes to train LLMs for text-to-speech (TTS) allows the LLM to generate the content and the style of the speech only from the text, similarly to humans, while the speaker identity is provided by the decoder of the VC model.

In-Context Learning Voice Conversion