CommonVoice

The sequence-to-sequence approach is widely used in speech recognition (SR) nowadays, and many research works are dedicated to show that their capabilities relying on a single architecture often match or are even better than traditional hybrid or CTC systems with separately optimized components.

Data and Resources

Cite this as

R. Ardila, M. Branson, K. Davis, M. Kohler, J. Meyer, M. Henretty, R. Morais, L. Saunders, F. M. Tyers, G. Weber (2024). Dataset: CommonVoice. https://doi.org/10.57702/xha9x66k

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.21437/Interspeech.2024-472
Citation
  • https://doi.org/10.48550/arXiv.2205.12304
Author R. Ardila
More Authors
M. Branson
K. Davis
M. Kohler
J. Meyer
M. Henretty
R. Morais
L. Saunders
F. M. Tyers
G. Weber
Homepage https://commonvoice.mozilla.org/