Speech Recognition

Here we include the list of available datasets as well as important publications on speech recognition via artificial neural networks.

Datasets

Switchboard hub 500

LibriSpeech

Publications

Architecture:ContextNet

Year:2020

Paper:Park, Daniel S., et al. “Improved Noisy Student Training for Automatic Speech Recognition.” arXiv preprint arXiv:2005.09629 (2020).

Architecture:GatedConvNet

Year:2018

Paper:Liptchinsky, Vitaliy, Gabriel Synnaeve, and Ronan Collobert. “Letter-based speech recognition with gated convnets.” CoRR, vol. abs/1712.09444 1 (2017).

Architecture:Deep Speech 2

Year:2016

Paper:Amodei, Dario, et al. “Deep speech 2: End-to-end speech recognition in english and mandarin.” International conference on machine learning. 2016.

Architecture:BRNN + Attention

Year:2015

Paper:Chorowski, Jan K., et al. “Attention-based models for speech recognition.” Advances in neural information processing systems. 2015.

Architecture:IBM2015

Year:2015

Paper:Saon, George, et al. “The IBM 2015 English conversational telephone speech recognition system.” arXiv preprint arXiv:1505.05899 (2015).

Architecture:Deep Speech

Year:2014

Paper:Hannun, Awni, et al. “Deep speech: Scaling up end-to-end speech recognition.” arXiv preprint arXiv:1412.5567 (2014).

Architecture:DNN + Dropout

Year:2014

Paper:Maas, Andrew L., et al. “Building DNN acoustic models for large vocabulary speech recognition.” Computer Speech & Language 41 (2017): 195-213.