Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding

12 February 2021

Papers citing "Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding"

7 / 7 papers shown

Title
End-to-End Neural Transformer Based Spoken Language Understanding Martin H. Radfar Athanasios Mouchtaris Siegfried Kunzmann 52 61 0 12 Aug 2020
Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition Jinxi Guo Gautam Tiwari J. Droppo Maarten Van Segbroeck Che-Wei Huang A. Stolcke Roland Maas 21 55 0 27 Jul 2020
DIET: Lightweight Language Understanding for Dialogue Systems Tanja Bunk Daksh Varshneya Vladimir Vlasov Alan Nichol 39 162 0 21 Apr 2020
Speech Model Pre-training for End-to-End Spoken Language Understanding Loren Lugosch Mirco Ravanelli Patrick Ignoto Vikrant Singh Tomar Yoshua Bengio SyDa AuLLM 39 349 0 07 Apr 2019
From Audio to Semantics: Approaches to end-to-end spoken language understanding Parisa Haghani A. Narayanan M. Bacchiani Galen Chuang Neeraj Gaur Pedro J. Moreno Rohit Prabhavalkar Zhongdi Qu Austin Waters 28 150 0 24 Sep 2018
State-of-the-art Speech Recognition With Sequence-to-Sequence Models Chung-Cheng Chiu Tara N. Sainath Yonghui Wu Rohit Prabhavalkar Patrick Nguyen ... Katya Gonina Navdeep Jaitly Yue Liu J. Chorowski M. Bacchiani AI4TS 63 1,150 0 05 Dec 2017
Sequence Transduction with Recurrent Neural Networks Alex Graves 56 1,858 0 14 Nov 2012