Papers › ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition...
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
Wei Han, Zhengdong Zhang, Yu Zhang, Jiahui Yu, Chung-Cheng Chiu, James Qin, Anmol Gulati, Ruoming Pang, Yonghui Wu
Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel CNN-RNN-transducer architecture, which we call ContextNet. ContextNet features a fully convolutional encoder that incorporates global context information into convolution layers by adding squeeze-and-excitation modules. In addition, we propose a simple scaling method that scales the widths of ContextNet that achieves good trade-off between computation and accuracy. We demonstrate that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate (WER) of 2.1%/4.6% without external language model (LM), 1.9%/4.1% with LM and 2.9%/7.0% with only 10M parameters on the clean/noisy LibriSpeech test sets. This compares to the previous best published system of 2.0%/4.6% with LM and 3.9%/11.3% with 20M parameters. The superiority of the proposed ContextNet model is also verified on a much larger internal dataset.
In Syntology 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 | LibriSpeech test-clean | ContextNet(L) | Word Error Rate (WER) | 1.9 | #17 of 64 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-clean | ContextNet(M) | Word Error Rate (WER) | 2 | #20 of 64 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-clean | ContextNet(S) | Word Error Rate (WER) | 2.3 | #36 of 64 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-other | ContextNet(L) | Word Error Rate (WER) | 4.1 | #18 of 53 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-other | ContextNet(M) | Word Error Rate (WER) | 4.5 | #27 of 53 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-other | ContextNet(S) | Word Error Rate (WER) | 5.5 | #33 of 53 | 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