1. MAESTRO: Matched Speech Text Representations through Modality Matching
2. Towards Reducing the Need for Speech Training Data to Build Spoken Language Understanding Systems
3. Adafactor: Adaptive learning rates with sublinear memory cost;shazeer;International Conference on Machine Learning,2018
4. An Efficient Streaming NonRecurrent On-Device End-to-End Model with Improvements to Rare- Word Modeling;sainath;Proc INTERSPEECH,2021