Multi-Output RNN-T Joint Networks for Multi-Task Learning of ASR and Auxiliary Tasks
暂无分享,去创建一个
Tara N. Sainath | David Rybach | Ian McGraw | Hao Zhang | Ding Zhao | Shaojin Ding | Yanzhang He | Shuo-yiin Chang | Shankar Kumar | Weiran Wang
[1] Srikanth Ronanki,et al. Robust Prediction of Punctuation and Truecasing for Medical ASR , 2020, NLPMC.
[2] Guokun Lai,et al. Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing , 2020, NeurIPS.
[3] Khe Chai Sim,et al. Efficient Implementation of Recurrent Neural Network Transducer in Tensorflow , 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).
[4] Tara N. Sainath,et al. Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home , 2017, INTERSPEECH.
[5] Alex Graves,et al. Sequence Transduction with Recurrent Neural Networks , 2012, ArXiv.
[6] Johan Schalkwyk,et al. Filters for Efficient Composition of Weighted Finite-State Transducers , 2010, CIAA.