# Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition

arXiv: https://arxiv.org/abs/1908.05227 · HTML: https://mlsanity.com/paper/1908.05227/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2019.

## Built on by (most cited first, 5 of 5)

- [Contextual Semi-Supervised Learning: An Approach To Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems](https://mlsanity.com/paper/2104.03643/) (2021)
- [Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0](https://mlsanity.com/paper/2110.03560/) (2021)
- [Low Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System](https://mlsanity.com/paper/2106.09963/) (2021)
- [ILASR: Privacy-Preserving Incremental Learning for Automatic Speech Recognition at Production Scale](https://mlsanity.com/paper/2207.09078/) (2022)
- [Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer](https://mlsanity.com/paper/2207.14736/) (2022)

## Abstract (arXiv)

In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data. Additional unlabelled speech data is employed through a data selection mechanism to obtain the best hypothesized output, further used to retrain the seed model. However, uncertainties of the model may not be well captured with a single hypothesis. As opposed to this technique, we apply a dropout mechanism to capture the uncertainty by obtaining multiple hypothesized text transcripts of an speech recording. We assume that the diversity of automatically generated transcripts for an utterance will implicitly increase the reliability of the model. Finally, the data selection process is also applied on these hypothesized transcripts to reduce the uncertainty. Experiments on freely available TEDLIUM corpus and proprietary Adobe's internal dataset show that the proposed approach significantly reduces ASR errors, compared to the baseline model.