@article{acceleratinginferenceandlanguagemodel,
  title = {Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization},
  author = {Andrea Fasoli and Chia-Yu Chen and Mauricio Serrano and Swagath Venkataramani and George Saon and Xiaodong Cui and Brian Kingsbury and Kailash Gopalakrishnan},
  year = {2022},
  eprint = {2206.07882},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2206.07882v1},
}