1. Connectionist temporal classification
2. Sequence Transduction with Recurrent Neural Networks;Graves;arXiv preprint arXiv:1211.3711,2012
3. Attention-based Models for Speech Recognition;Chorowski;Neural Information Processing Systems (NeurIPS),2015
4. WeNet: Production Oriented Streaming and Non-Streaming End-to-End Speech Recognition Toolkit
5. Attention is All You Need;Vaswani;Neural Information Processing Systems (NeurIPS),2017