TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Audio/Speech Recognition/WSJ eval92

Speech Recognition on WSJ eval92

Metric: Word Error Rate (WER) (lower is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Word Error Rate (WER)▲Extra DataPaperDate↕Code
1Speechstew 100M1.3YesSpeechStew: Simply Mix All Available Speech Reco...2021-04-05-
2ConformerXXL-P1.3NoBigSSL: Exploring the Frontier of Large-Scale Se...2021-09-27-
3Task activating prompting generative correction2.11YesGenerative Speech Recognition Error Correction w...2023-09-27-
4RobustGER2.2YesIt's Never Too Late: Fusing Acoustic Information...2024-02-08Code
5tdnn + chain2.32No---
6CTC-CRF ST-NAS2.77NoEfficient Neural Architecture Search for End-to-...2020-11-11Code
7End-to-end LF-MMI3No---
8Transformer with Relaxed Attention3.19NoRelaxed Attention: A Simple Method to Boost Perf...2021-07-02Code
9CTC-CRF VGG-BLSTM3.2NoCAT: A CTC-CRF based ASR Toolkit Bridging the Hy...2020-05-27Code
10Espresso3.4NoEspresso: A Fast End-to-end Neural Speech Recogn...2019-09-18Code
11TC-DNN-BLSTM-DNN3.5NoDeep Recurrent Neural Networks for Acoustic Mode...2015-04-07-
12Convolutional Speech Recognition3.5NoFully Convolutional Speech Recognition2018-12-17-
13test-set on open vocabulary (i.e. harder), model = HMM-DNN + pNorm*3.6No---
14Deep Speech 23.6YesDeep Speech 2: End-to-End Speech Recognition in ...2015-12-08Code
15CTC-CRF 4gram-LM3.79No--Code
16CNN over RAW speech (wav)5.6No---
17Jasper 10x36.9NoJasper: An End-to-End Convolutional Neural Acous...2019-04-05Code