You're currently viewing an old version of this dataset. To see the current version, click here.

Very Deep Multilingual Convolutional Neural Networks for LVCSR

Convolutional neural networks (CNNs) are a standard component of many current state-of-the-art Large Vocabulary Continuous Speech Recognition (LVCSR) systems. However, CNNs in LVCSR have not kept pace with recent advances in other domains where deeper neural networks provide superior performance.

Data and Resources

Cite this as

Tom Sercu, Christian Puhrsch, Brian Kingsbury, Yann LeCun (2024). Dataset: Very Deep Multilingual Convolutional Neural Networks for LVCSR. https://doi.org/10.57702/afrwxtoz

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Tom Sercu
More Authors
Christian Puhrsch
Brian Kingsbury
Yann LeCun