# Dysfluent WFST: A Framework for Zero-Shot Speech Dysfluency Transcription and Detection

arXiv: https://arxiv.org/abs/2505.16351 · HTML: https://mlsanity.com/paper/2505.16351/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 23 of 23)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Universal Phone Recognition with a Multilingual Allophone System](https://mlsanity.com/paper/2002.11800/) (2020)
- [Simple and Effective Zero-shot Cross-lingual Phoneme Recognition](https://mlsanity.com/paper/2109.11680/) (2021)
- [From LLM to NMT: Advancing Low-Resource Machine Translation with Claude](https://mlsanity.com/paper/2404.13813/) (2024)
- [Disfluency Detection using a Bidirectional LSTM](https://mlsanity.com/paper/1604.03209/) (2016)
- [Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0](https://mlsanity.com/paper/2204.03417/) (2022)
- [Unconstrained Dysfluency Modeling for Dysfluent Speech Transcription and Detection](https://mlsanity.com/paper/2312.12810/) (2023)
- [Coding Speech through Vocal Tract Kinematics](https://mlsanity.com/paper/2406.12998/) (2024)
- [YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection](https://mlsanity.com/paper/2408.15297/) (2024)
- [Towards Hierarchical Spoken Language Dysfluency Modeling](https://mlsanity.com/paper/2401.10015/) (2024)
- [SSDM: Scalable Speech Dysfluency Modeling](https://mlsanity.com/paper/2408.16221/) (2024)
- [Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition](https://mlsanity.com/paper/2204.00465/) (2022)
- [Deep Speech Synthesis from MRI-Based Articulatory Representations](https://mlsanity.com/paper/2307.02471/) (2023)
- [Enhancing ASR for Stuttered Speech with Limited Data Using Detect and Pass](https://mlsanity.com/paper/2202.05396/) (2022)
- [Articulatory Representation Learning Via Joint Factor Analysis and Neural Matrix Factorization](https://mlsanity.com/paper/2210.16498/) (2022)
- [Large Language Models for Dysfluency Detection in Stuttered Speech](https://mlsanity.com/paper/2406.11025/) (2024)
- [Stutter-Solver: End-to-end Multi-lingual Dysfluency Detection](https://mlsanity.com/paper/2409.09621/) (2024)
- [Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling](https://mlsanity.com/paper/2306.00996/) (2023)
- [Time and Tokens: Benchmarking End-to-End Speech Dysfluency Detection](https://mlsanity.com/paper/2409.13582/) (2024)
- [Self-supervised Speech Models for Word-Level Stuttered Speech Detection](https://mlsanity.com/paper/2409.10704/) (2024)
- [SSDM 2.0: Time-Accurate Speech Rich Transcription with Non-Fluencies](https://mlsanity.com/paper/2412.00265/) (2024)

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

- [Seamless Dysfluent Speech Text Alignment for Disordered Speech Analysis](https://mlsanity.com/paper/2506.12073/) (2025)
- [HuPER: A Human-Inspired Framework for Phonetic Perception](https://mlsanity.com/paper/2602.01634/) (2026)
- [K-Function: Joint Pronunciation Transcription and Feedback for Evaluating Kids Language Function](https://mlsanity.com/paper/2507.03043/) (2025)
- [A Comparative Study of Controllability, Explainability, and Performance in Dysfluency Detection Models](https://mlsanity.com/paper/2509.00058/) (2025)
- [Deploying UDM Series in Real-Life Stuttered Speech Applications: A Clinical Evaluation Framework](https://mlsanity.com/paper/2509.14304/) (2025)

## Abstract (arXiv)

Automatic detection of speech dysfluency aids speech-language pathologists in efficient transcription of disordered speech, enhancing diagnostics and treatment planning. Traditional methods, often limited to classification, provide insufficient clinical insight, and text-independent models misclassify dysfluency, especially in context-dependent cases. This work introduces Dysfluent-WFST, a zero-shot decoder that simultaneously transcribes phonemes and detects dysfluency. Unlike previous models, Dysfluent-WFST operates with upstream encoders like WavLM and requires no additional training. It achieves state-of-the-art performance in both phonetic error rate and dysfluency detection on simulated and real speech data. Our approach is lightweight, interpretable, and effective, demonstrating that explicit modeling of pronunciation behavior in decoding, rather than complex architectures, is key to improving dysfluency processing systems.