Robust Speech Recognition via Large-Scale Weak Supervision

Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine Mcleavey, Ilya Sutskever
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28492-28518, 2023.

Abstract

We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results without the need for any dataset specific fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-radford23a, title = {Robust Speech Recognition via Large-Scale Weak Supervision}, author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and Mcleavey, Christine and Sutskever, Ilya}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {28492--28518}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/radford23a/radford23a.pdf}, url = {https://proceedings.mlr.press/v202/radford23a.html}, abstract = {We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results without the need for any dataset specific fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.} }
Endnote
%0 Conference Paper %T Robust Speech Recognition via Large-Scale Weak Supervision %A Alec Radford %A Jong Wook Kim %A Tao Xu %A Greg Brockman %A Christine Mcleavey %A Ilya Sutskever %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-radford23a %I PMLR %P 28492--28518 %U https://proceedings.mlr.press/v202/radford23a.html %V 202 %X We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results without the need for any dataset specific fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.
APA
Radford, A., Kim, J.W., Xu, T., Brockman, G., Mcleavey, C. & Sutskever, I.. (2023). Robust Speech Recognition via Large-Scale Weak Supervision. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:28492-28518 Available from https://proceedings.mlr.press/v202/radford23a.html.

Related Material