A Simplified Fully Quantized Transformer for End-to-end Speech Recognition
arXiv.org, 2020-032020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;http://arxiv.org/licenses/nonexclusive-distrib/1.0 ;EISSN: 2331-8422 ;DOI: 10.48550/arxiv.1911.03604
Full text available