# Adversarial Training For Low-Resource Disfluency Correction

arXiv: https://arxiv.org/abs/2306.06384 · HTML: https://mlsanity.com/paper/2306.06384/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 34 references that are in the map.
- First posted on arXiv 10 Jun 2023.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [MuRIL: Multilingual Representations for Indian Languages](https://mlsanity.com/paper/2103.10730/) (2021)
- [Disfluency Detection using a Bidirectional LSTM](https://mlsanity.com/paper/1604.03209/) (2016)
- [Improving Disfluency Detection by Self-Training a Self-Attentive Model](https://mlsanity.com/paper/2004.05323/) (2020)
- [Disfluency Detection using a Noisy Channel Model and a Deep Neural Language Model](https://mlsanity.com/paper/1808.09091/) (2018)
- [LARD: Large-scale Artificial Disfluency Generation](https://mlsanity.com/paper/2201.05041/) (2022)
- [Span Classification with Structured Information for Disfluency Detection in Spoken Utterances](https://mlsanity.com/paper/2203.16028/) (2022)

## Built on by (most cited first, 3 of 3)

- [The Zeno's Paradox of `Low-Resource' Languages](https://mlsanity.com/paper/2410.20817/) (2024)
- [DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European Languages](https://mlsanity.com/paper/2310.16749/) (2023)
- [Aligning Stuttered-Speech Research with End-User Needs: Scoping Review, Survey, and Guidelines](https://mlsanity.com/paper/2604.20535/) (2026)

## Abstract (arXiv)

Disfluencies commonly occur in conversational speech. Speech with disfluencies can result in noisy Automatic Speech Recognition (ASR) transcripts, which affects downstream tasks like machine translation. In this paper, we propose an adversarially-trained sequence-tagging model for Disfluency Correction (DC) that utilizes a small amount of labeled real disfluent data in conjunction with a large amount of unlabeled data. We show the benefit of our proposed technique, which crucially depends on synthetically generated disfluent data, by evaluating it for DC in three Indian languages- Bengali, Hindi, and Marathi (all from the Indo-Aryan family). Our technique also performs well in removing stuttering disfluencies in ASR transcripts introduced by speech impairments. We achieve an average 6.15 points improvement in F1-score over competitive baselines across all three languages mentioned. To the best of our knowledge, we are the first to utilize adversarial training for DC and use it to correct stuttering disfluencies in English, establishing a new benchmark for this task.