Published September 2, 2024 | Version v1
Conference paper Open

Multi-speaker and Multi-dialectal Catalan TTS Models for Video Gaming

Description

Recently, we explored and trained different state-of-the-art text-to-speech (TTS) architectures for Catalan. We used existing datasets but also produced a new Catalan multi-accent dataset to train these architectures. The objective of our work is to improve the quality of current TTS systems in Catalan and export the resulting models for potential interactive applications and video games. 

Files

Publication_Interspeech_2024.pdf

Files (158.7 kB)

Name Size Download all
md5:065a29a44113c973c1be602dab0289f6
158.7 kB Preview Download

Additional details

Dates

Accepted
2024-09-02