mlsanityData to 14 Oct 2026

Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectives

arXiv 2301.10761 ↗First posted 25 Jan 2023cs.CL cs.HCcited by 5

Not on the map. Why?

Abstract (arXiv)

Disfluencies (i.e. interruptions in the regular flow of speech), are ubiquitous to spoken discourse. Fillers ("uh", "um") are disfluencies that occur the most frequently compared to other kinds of disfluencies. Yet, to the best of our knowledge, there isn't a resource that brings together the research perspectives influencing Spoken Language Understanding (SLU) on these speech events. This aim of this article is to survey a breadth of perspectives in a holistic way; i.e. from considering underlying (psycho)linguistic theory, to their annotation and consideration in Automatic Speech Recognition (ASR) and SLU systems, to lastly, their study from a generation standpoint. This article aims to present the perspectives in an approachable way to the SLU and Conversational AI community, and discuss moving forward, what we believe are the trends and challenges in each area.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 25 of its 114 references that are in the map. First posted on arXiv 25 Jan 2023.

Builds on

25 of 114 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  3. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 210
  4. 2019FlauBERT: Unsupervised Language Model Pre-training for Frenchcited by 153
  5. 2021Anticipating Safety Issues in E2E Conversational AI: Framework and Toolingcited by 78
  6. 2020Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Surveycited by 51
  7. 2021"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversationscited by 30
  8. 2019Recent Trends in Deep Learning Based Personality Detectioncited by 29
  9. 2021Alzheimer's Dementia Recognition Using Acoustic, Lexical, Disfluency and Speech Pause Features Robust to Noisy Inputscited by 27
  10. 2020Improving Disfluency Detection by Self-Training a Self-Attentive Modelcited by 25
  11. 2019Fluent Translations from Disfluent Speech in End-to-End Speech Translationcited by 22
  12. 2019Disfluencies and Human Speech Transcription Errorscited by 21
13 more
  1. 2020End-to-End Speech Recognition and Disfluency Removalcited by 16
  2. 2020The importance of fillers for text representations of speech transcriptscited by 15
  3. 2022Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detectioncited by 12
  4. 2019Giving Attention to the Unexpected: Using Prosody Innovations in Disfluency Detectioncited by 11
  5. 2022Risk-graded Safety for Handling Medical Queries in Conversational AIcited by 11
  6. 2020On the Role of Style in Parsing Speech with Neural Modelscited by 7
  7. 2022Filler Word Detection and Classification: A Dataset and Benchmarkcited by 7
  8. 2020Re-framing Incremental Deep Language Models for Dialogue Processing with Multi-task Learningcited by 4
  9. 2018DisMo: A Morphosyntactic, Disfluency and Multi-Word Unit Annotator. An Evaluation on a Corpus of French Spontaneous and Read Speechcited by 3
  10. 2018Multi-Task Learning for Domain-General Spoken Disfluency Detection in Dialogue Systemscited by 3
  11. 2017Parsing Speech: A Neural Approach to Integrating Lexical and Acoustic-Prosodic Informationcited by 2
  12. 2018Opinion Dynamics Modeling for Movie Review Transcripts Classification with Hidden Conditional Random Fieldscited by 2
  13. 2018Increase Apparent Public Speaking Fluency By Speech Augmentationcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 2.

5 papers.

  1. 2023Mirages: On Anthropomorphism in Dialogue Systemscited by 30
  2. 2023Putting Natural in Natural Language Processingcited by 17
  3. 2024Boosting Disfluency Detection with Large Language Model as Disfluency Generatorcited by 2
  4. 2025Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbonescited by 2
  5. 2025Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Modelscited by 1