Paper: Towards Learning a Universal Non-Semantic Representation of Speech
- Reproduce the results from our paper
- Compute performance of a new embedding on the Non-Semantic Speech Benchmark (NOSS)
- Run our embedding TRILL, or any of the other embedding networks on a new dataset.
To use this benchmark or embeddings, please cite as follows:
@article{shor2020,
title={Towards Learning a Universal Non-Semantic Representation of Speech},
author={Joel Shor and Aren Jansen and Ronnie Maor and Oran Lang and Omry Tuval and Felix de Chaumont Quitry and Marco Tagliasacchi and Ira Shavitt and Dotan Emanuel and Yinnon Haviv},
year={2020},
journal = {ArXiv e-prints},
eprint={2002.12764},
archivePrefix={arXiv},
primaryClass={eess.AS},
url = {https://arxiv.org/abs/2002.12764}
}
Joel Shor (joelshor@google.com)
Oran Lang (oranl@google.com)