README.md

metadata

tags:
  - model_hub_mixin
  - pytorch_model_hub_mixin
license: apache-2.0
datasets:
  - speechcolab/gigaspeech
  - facebook/multilingual_librispeech
language:
  - en
pipeline_tag: text-to-speech

Model Card

Token-Voicebox, a model following the Voicebox architecture, reconstructs speech from speech tokens generated by USDM.

Paralinguistics-Aware Speech-Empowered LLMs for Natural Conversation [NeurIPS 2024]

• Repository: https://github.com/naver-ai/usdm
• Paper: https://openreview.net/forum?id=NjewXJUDYq
• Project Page: https://unifiedsdm.github.io/

BibTeX

@inproceedings{
  kim2024paralinguisticsaware,
  title={Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation},
  author={Heeseung Kim and Soonshin Seo and Kyeongseok Jeong and Ohsung Kwon and Soyoon Kim and Jungwhan Kim and Jaehong Lee and Eunwoo Song and Myungwoo Oh and Jung-Woo Ha and Sungroh Yoon and Kang Min Yoo},
  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year={2024},
  url={https://openreview.net/forum?id=NjewXJUDYq}
}