Publications
-
DeepSpeech: Scaling up end-to-end speech recognition
See publicationWe present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments.
-
Real-time Parallel Hashing on the GPU
Transactions on Graphics (TOG), Volume 28, Issue 5 Proc. of ACM SIGGRAPH ASIA 2009
Patents
Other similar profiles
Explore top content on LinkedIn
Find curated posts and insights for relevant topics all in one place.
View top content