# Reducing Exposure Bias in Training Recurrent Neural Network Transducers

arXiv: https://arxiv.org/abs/2108.10803 · HTML: https://mlsanity.com/paper/2108.10803/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 24 Aug 2021.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [End-to-End Attention-based Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1508.04395/) (2015)
- [A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition](https://mlsanity.com/paper/2002.11268/) (2020)
- [SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation](https://mlsanity.com/paper/1808.07512/) (2018)
- [Advancing RNN Transducer Technology for Speech Recognition](https://mlsanity.com/paper/2103.09935/) (2021)
- [English Conversational Telephone Speech Recognition by Humans and Machines](https://mlsanity.com/paper/1703.02136/) (2017)
- [Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard](https://mlsanity.com/paper/2001.07263/) (2020)
- [Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding](https://mlsanity.com/paper/1911.00203/) (2019)

## Built on by (most cited first, 2 of 2)

- [Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition](https://mlsanity.com/paper/2110.03841/) (2021)
- [O-1: Self-training with Oracle and 1-best Hypothesis](https://mlsanity.com/paper/2308.07486/) (2023)

## Abstract (arXiv)

When recurrent neural network transducers (RNNTs) are trained using the typical maximum likelihood criterion, the prediction network is trained only on ground truth label sequences. This leads to a mismatch during inference, known as exposure bias, when the model must deal with label sequences containing errors. In this paper we investigate approaches to reducing exposure bias in training to improve the generalization of RNNT models for automatic speech recognition (ASR). A label-preserving input perturbation to the prediction network is introduced. The input token sequences are perturbed using SwitchOut and scheduled sampling based on an additional token language model. Experiments conducted on the 300-hour Switchboard dataset demonstrate their effectiveness. By reducing the exposure bias, we show that we can further improve the accuracy of a high-performance RNNT ASR model and obtain state-of-the-art results on the 300-hour Switchboard dataset.