Papers › Jasper: An End-to-End Convolutional Neural Acoustic Model
Jasper: An End-to-End Convolutional Neural Acoustic Model
Jason Li, Vitaly Lavrukhin, Boris Ginsburg, Ryan Leary, Oleksii Kuchaiev, Jonathan M. Cohen, Huyen Nguyen, Ravi Teja Gadde
In this paper, we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data. Our model, Jasper, uses only 1D convolutions, batch normalization, ReLU, dropout, and residual connections. To improve training, we further introduce a new layer-wise optimizer called NovoGrad. Through experiments, we demonstrate that the proposed deep architecture performs as well or better than more complex choices. Our deepest Jasper variant uses 54 convolutional layers. With this architecture, we achieve 2.95% WER using a beam-search decoder with an external neural language model and 3.86% WER with a greedy decoder on LibriSpeech test-clean. We also report competitive results on the Wall Street Journal and the Hub5'00 conversational evaluation datasets.
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Speech Recognition | Hub5'00 SwitchBoard | Jasper DR 10x5 | CallHome | 16.2 | #3 of 5 | Archive leaderboard | report |
| Speech Recognition | Hub5'00 SwitchBoard | Jasper DR 10x5 | SwitchBoard | 7.8 | #3 of 5 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-clean | Jasper DR 10x5 (+ Time/Freq Masks) | Word Error Rate (WER) | 2.84 | #45 of 64 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-clean | Jasper DR 10x5 | Word Error Rate (WER) | 2.95 | #46 of 64 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-other | Jasper DR 10x5 (+ Time/Freq Masks) | Word Error Rate (WER) | 7.84 | #43 of 53 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-other | Jasper DR 10x5 | Word Error Rate (WER) | 8.79 | #45 of 53 | Archive leaderboard | report |
| Speech Recognition | WSJ eval92 | Jasper 10x3 | Word Error Rate (WER) | 6.9 | #17 of 17 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections