| SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network | | 1.3 | Speechstew 100M | 2021-04-05 |
| BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition | | 1.3 | ConformerXXL-P | 2021-09-27 |
| Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting | | 2.11 | Task activating prompting generative correction | 2023-09-27 |
| It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition | ✓ Link | 2.2 | RobustGER | 2024-02-08 |
| Purely sequence-trained neural networks for ASR based on lattice-free MMI | | 2.32 | tdnn + chain | 2016-09-08 |
| Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients | ✓ Link | 2.77 | CTC-CRF ST-NAS | 2020-11-11 |
| End-to-end speech recognition using lattice-free MMI | | 3.0 | End-to-end LF-MMI | 2018-09-06 |
| Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition | ✓ Link | 3.19 | Transformer with Relaxed Attention | 2021-07-02 |
| CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency | ✓ Link | 3.2 | CTC-CRF VGG-BLSTM | 2020-05-27 |
| Espresso: A Fast End-to-end Neural Speech Recognition Toolkit | ✓ Link | 3.4 | Espresso | 2019-09-18 |
| Deep Recurrent Neural Networks for Acoustic Modelling | | 3.5 | TC-DNN-BLSTM-DNN | 2015-04-07 |
| Fully Convolutional Speech Recognition | | 3.5 | Convolutional Speech Recognition | 2018-12-17 |
| []() | | 3.6 | test-set on open vocabulary (i.e. harder), model = HMM-DNN + pNorm* | |
| Deep Speech 2: End-to-End Speech Recognition in English and Mandarin | ✓ Link | 3.60 | Deep Speech 2 | 2015-12-08 |
| CRF-based Single-stage Acoustic Modeling with CTC Topology | ✓ Link | 3.79 | CTC-CRF 4gram-LM | 2019-04-16 |
| []() | | 5.6 | CNN over RAW speech (wav) | |
| Jasper: An End-to-End Convolutional Neural Acoustic Model | ✓ Link | 6.9 | Jasper 10x3 | 2019-04-05 |