ICASSP 2025accepted0 citations
LIMMITS'25: Multilingual Streaming TTS With Neural Codecs for Indian Languages
Philipp Olbrich, Hema A. Murthy, Pranaw Kumar, Shinji Watanabe, Sheng Zhao, Mark Hasegawa-Johnson
Abstract
This work provides a summary of the Multilingual streaming TTS with neural codecs for Indian languages challenge (LIMMITS’25), organized as part of the ICASSP 2025 signal processing grand challenge. Towards this, 278 hours of TTS data in 4 Indian languages - Gujarati, Indian English, Bhojpuri, and Kannada got released. The challenge focuses on advancing research in neural codec-based and streaming TTS systems. The top teams in the challenge attained high subjective scores on naturalness and similarity, thus contributing to the progress in text-to-speech generation systems.
BibTeX
@inproceedings{icassp2025_limmits25multili,
title = {LIMMITS'25: Multilingual Streaming TTS With Neural Codecs for Indian Languages},
author = {Philipp Olbrich and Hema A. Murthy and Pranaw Kumar and Shinji Watanabe and Sheng Zhao and Mark Hasegawa-Johnson},
booktitle = {ICASSP 2025},
year = {2025}
}