O-1: Self-training with Oracle and 1-best Hypothesis

O-1: Self-training with Oracle and 1-best Hypothesis

14 August 2023

Andrew Rosenberg

Bhuvana Ramabhadran

Kartik Audhkhasi

Papers citing "O-1: Self-training with Oracle and 1-best Hypothesis"

11 / 11 papers shown

Title
SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network William Chan Daniel S. Park Chris A. Lee Yu Zhang Quoc V. Le Mohammad Norouzi AI4TS 70 138 0 05 Apr 2021
On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer Liang Lu Zhong Meng Naoyuki Kanda Jinyu Li Jiawei Liu 55 12 0 23 Oct 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 40 55 0 27 Jul 2020
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations Alexei Baevski Henry Zhou Abdel-rahman Mohamed Michael Auli SSL 228 5,774 0 20 Jun 2020
Conformer: Convolution-augmented Transformer for Speech Recognition Anmol Gulati James Qin Chung-Cheng Chiu Niki Parmar Yu Zhang ... Wei Han Shibo Wang Zhengdong Zhang Yonghui Wu Ruoming Pang 210 3,119 0 16 May 2020
Recognizing long-form speech using streaming end-to-end models A. Narayanan Rohit Prabhavalkar Chung-Cheng Chiu David Rybach Tara N. Sainath Trevor Strohman 61 130 0 24 Oct 2019
Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation? Tianxing He Jingzhao Zhang Zhiming Zhou James R. Glass 69 32 0 25 May 2019
SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing Taku Kudo John Richardson 175 3,514 0 19 Aug 2018
Sequence Level Training with Recurrent Neural Networks MarcÁurelio Ranzato S. Chopra Michael Auli Wojciech Zaremba 96 1,614 0 20 Nov 2015
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks Samy Bengio Oriol Vinyals Navdeep Jaitly Noam M. Shazeer 133 2,032 0 09 Jun 2015
Sequence Transduction with Recurrent Neural Networks Alex Graves 171 1,866 0 14 Nov 2012