# Auxiliary Sequence Labeling Tasks for Disfluency Detection

arXiv: https://arxiv.org/abs/2011.04512 · HTML: https://mlsanity.com/paper/2011.04512/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [Streaming Joint Speech Recognition and Disfluency Detection](https://mlsanity.com/paper/2211.08726/) (2022)
- [Span Classification with Structured Information for Disfluency Detection in Spoken Utterances](https://mlsanity.com/paper/2203.16028/) (2022)
- [Boosting Disfluency Detection with Large Language Model as Disfluency Generator](https://mlsanity.com/paper/2403.08229/) (2024)
- [A novel multimodal dynamic fusion network for disfluency detection in spoken utterances](https://mlsanity.com/paper/2211.14700/) (2022)
- [Improving Distinction between ASR Errors and Speech Disfluencies with Feature Space Interpolation](https://mlsanity.com/paper/2108.01812/) (2021)
- [End-to-End Speech Recognition and Disfluency Removal with Acoustic Language Model Pretraining](https://mlsanity.com/paper/2309.04516/) (2023)

## Abstract (arXiv)

Detecting disfluencies in spontaneous speech is an important preprocessing step in natural language processing and speech recognition applications. Existing works for disfluency detection have focused on designing a single objective only for disfluency detection, while auxiliary objectives utilizing linguistic information of a word such as named entity or part-of-speech information can be effective. In this paper, we focus on detecting disfluencies on spoken transcripts and propose a method utilizing named entity recognition (NER) and part-of-speech (POS) as auxiliary sequence labeling (SL) tasks for disfluency detection. First, we investigate cases that utilizing linguistic information of a word can prevent mispredicting important words and can be helpful for the correct detection of disfluencies. Second, we show that training a disfluency detection model with auxiliary SL tasks can improve its F-score in disfluency detection. Then, we analyze which auxiliary SL tasks are influential depending on baseline models. Experimental results on the widely used English Switchboard dataset show that our method outperforms the previous state-of-the-art in disfluency detection.