- ASR II
- RNN-Transducer archetecture
- Language model fusion methods
- Byte-pair encoding
TODO: add seminar notebook here
All links are provided on the last slide of the lecture
- (blog post) Neural text generation: How to generate text using conditional language models
- (paper) A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition
- (paper) Sequence Transduction with Recurrent Neural Networks
- (paper) Improving RNN Transducer Modeling for End-to-End Speech Recognition
- (paper) Streaming End-to-end Speech Recognition For Mobile Devices
- (paper) Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks