Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer

29 July 2022

Papers citing "Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer"

19 / 19 papers shown

Title
Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network Janne Pylkkönen Antti Ukkonen Juho Kilpikoski Samu Tamminen Hannes Heikinheimo 48 27 0 22 Apr 2021
Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition Cong-Thanh Do R. Doddipatla Thomas Hain 37 6 0 29 Mar 2021
Advancing RNN Transducer Technology for Speech Recognition G. Saon Zoltan Tueske Daniel Bolaños Brian Kingsbury 92 88 0 17 Mar 2021
Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training Sameer Khurana Niko Moritz Takaaki Hori Jonathan Le Roux 63 58 0 26 Nov 2020
Semi-Supervised Speech Recognition via Graph-based Temporal Classification Niko Moritz Takaaki Hori Jonathan Le Roux 107 28 0 29 Oct 2020
Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview P. Bell Joachim Fainberg Ondˇrej Klejch Jinyu Li Steve Renals P. Swietojanski 100 78 0 14 Aug 2020
Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability Jinyu Li Rui Zhao Zhong Meng Yanqing Liu Wenning Wei ... V. Mazalov Zhenghao Wang Lei He Sheng Zhao Jiawei Liu 63 109 0 30 Jul 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 51 55 0 27 Jul 2020
On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition Jinyu Li Yu-Huan Wu Yashesh Gaur Chengyi Wang Rui Zhao Shujie Liu 54 137 0 28 May 2020
PyTorch: An Imperative Style, High-Performance Deep Learning Library Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury ... Sasank Chilamkurthy Benoit Steiner Lu Fang Junjie Bai Soumith Chintala ODL 556 42,639 0 03 Dec 2019
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures Gabriel Synnaeve Qiantong Xu Jacob Kahn Tatiana Likhomanenko Edouard Grave Vineel Pratap Anuroop Sriram Vitaliy Liptchinsky R. Collobert SSL AI4TS 117 247 0 19 Nov 2019
Improving RNN Transducer Modeling for End-to-End Speech Recognition Jinyu Li Rui Zhao Hu Hu Jiawei Liu 60 170 0 26 Sep 2019
Self-Training for End-to-End Speech Recognition Jacob Kahn Ann Lee Awni Y. Hannun SSL 61 236 0 19 Sep 2019
Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition S. Dey P. Motlícek Trung H. Bui Franck Dernoncourt 33 13 0 08 Aug 2019
On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition Kazuki Irie Rohit Prabhavalkar Anjuli Kannan A. Bruguier David Rybach Patrick Nguyen 66 37 0 05 Feb 2019
ESPnet: End-to-End Speech Processing Toolkit Shinji Watanabe Takaaki Hori Shigeki Karita Tomoki Hayashi Jiro Nishitoba ... Jahn Heymann Sanjeev Khudanpur Nanxin Chen Adithya Renduchintala Tsubasa Ochiai VLM 120 1,514 0 30 Mar 2018
Exploring Neural Transducers for End-to-End Speech Recognition Eric Battenberg Jitong Chen R. Child Adam Coates Yashesh Gaur Yi Li ... Hairong Liu S. Satheesh David Seetapun Anuroop Sriram Zhenyao Zhu AI4TS 86 230 0 24 Jul 2017
An overview of gradient descent optimization algorithms Sebastian Ruder ODL 209 6,206 0 15 Sep 2016
Sequence Transduction with Recurrent Neural Networks Alex Graves 195 1,872 0 14 Nov 2012