Challenge: Disfluency detection is a challenging task because of its different metrics depending on whether the input features are text or speech.
Approach: They propose a framework for disfluency detection inspired by the clinical and the natural language processing perspective together with the theory of performance from (Clark, 1998) . they present a forced-aligned disfluence dataset and propose new audio features inspired by word-based span features.
Outcome: The proposed framework outperforms baselines for speech-based predictions on a forced-aligned disfluency dataset from semi-directed interviews.

Similar Papers

Giving Attention to the Unexpected: Using Prosody Innovations in Disfluency Detection (N19-1)

Copied to clipboard

Challenge: Disfluencies in spontaneous speech are associated with prosodic disruptions.
Approach: They propose a method to extract acoustic-prosodic cues from word transcripts . they explore early and late fusion techniques for integrating text and prosody .
Outcome: The proposed approach shows gains over a high-accuracy text-only model.
Integrating Disfluency-based and Prosodic Features with Acoustics in Automatic Fluency Evaluation of Spontaneous Speech (2020.lrec-1)

Copied to clipboard

Challenge: acoustics, prosody, and disfluency-based features are used to evaluate fluent/disfluent speech . filling pauses and word fragments are used for automatic fluency evaluation .
Approach: They integrate acoustics, prosody, and disfluency-based features into an automatic fluency evaluation task.
Outcome: The proposed model improves when integrated with prosodic features, but not when disfluent speech is detected.
Lost in Transcription: Identifying and Quantifying the Accuracy Biases of Automatic Speech Recognition Systems Against Disfluent Speech (2024.naacl-long)

Copied to clipboard

Challenge: Automatic speech recognition systems fail to accurately interpret speech patterns deviating from typical fluency, leading to critical usability issues and misinterpretations.
Approach: They evaluate six leading automatic speech recognition systems based on a real-world dataset and a synthetic dataset derived from the widely-used LibriSpeech benchmark.
Outcome: The six leading speech recognition systems were evaluated on a real-world dataset and a synthetic dataset derived from the widely-used LibriSpeech benchmark.
End-to-End Speech Recognition and Disfluency Removal (2020.findings-emnlp)

Copied to clipboard

Challenge: Disfluency detection is usually an intermediate step between an automatic speech recognition system and a downstream task.
Approach: They propose to train models to directly map disfluent speech into fluent transcripts without relying on a separate disfluency detection model.
Outcome: The proposed models learn to generate fluent transcripts, but their performance is slightly worse than a baseline pipeline approach consisting of an ASR system and a specialized disfluency detection model.
Adversarial Training for Low-Resource Disfluency Correction (2023.findings-acl)

Copied to clipboard

Challenge: Disfluencies can be introduced in conversational speech due to the conversational nature of speech and/or speech impairments such as stuttering.
Approach: They propose an adversarial sequence-tagging model for Disfluency Correction . they evaluate it in Bengali, Hindi, and Marathi languages and use it to correct stuttering disfluencies .
Outcome: The proposed technique improves in Bengali, Hindi, and Marathi languages . it also removes stuttering disfluencies in ASR transcripts introduced by speech impairments .
Semantic Parsing of Disfluent Speech (2021.eacl-main)

Copied to clipboard

Challenge: Semantic parsing is a key component for understanding user utterances in voice assistants . however, most research on disfluent speech is focused on written text .
Approach: They investigate semantic parsing of disfluent speech with the ATIS dataset . they add real and synthetic disfluencies at training time to improve model performance .
Outcome: The proposed parser outperforms the state-of-the-art parsers on the ATIS dataset in terms of performance and accuracy.
Using the RUPEX Multichannel Corpus in a Pilot fMRI Study on Speech Disfluencies (2020.lrec-1)

Copied to clipboard

Challenge: Numerous classifications of disfluencies have been proposed and/or implemented in annotating speech corpora.
Approach: They propose to use Russian multichannel corpus RUPEX to create fragments of speech disfluencies and their clusters.
Outcome: The proposed method allows to create fragments in terms of requirements for the fMRI BOLD temporal resolution.
Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs (2026.acl-long)

Copied to clipboard

Challenge: Spontaneous speech is rarely fluent, and disfluencies can degrade readability and reliability . a sequence tagger first marks disfluent tokens, and these signals guide instruction fine-tuning .
Approach: They propose a multilingual correction pipeline where a sequence tagger first marks disfluent tokens . they add a contrastive learning objective that penalizes the reproduction of disfluency tokens.
Outcome: The proposed model improves readability and reliability of ASR transcripts in three languages . disfluencies can cause misinterpretations, incoherent responses, poor user experience .
Disfluency Generation for More Robust Dialogue Systems (2023.findings-acl)

Copied to clipboard

Challenge: Disfluencies in user utterances can trigger a chain of errors impacting all the modules of a dialogue system.
Approach: They propose to augment existing dialogue datasets with disfluent utterances by paraphrasing them into disfluente ones.
Outcome: The proposed method improves dialogue state tracking and response generation by combining disfluent utterances with disfluency utteraces.
Planning and Generating Natural and Diverse Disfluent Texts as Augmentation for Disfluency Detection (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to disfluency detection heavily depend on labeled data.
Approach: They propose a Planner-Generator based disfluency generation model that generates natural disfluent texts as augmented data.
Outcome: The proposed model outperforms baselines and leads to state-of-the-art performance on Switchboard corpus.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations