# The Influence of Dataset Partitioning on Dysfluency Detection Systems

arXiv: https://arxiv.org/abs/2206.03400 · HTML: https://mlsanity.com/paper/2206.03400/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 7 Jun 2022.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings](https://mlsanity.com/paper/2104.03502/) (2021)
- [SEP-28k: A Dataset for Stuttering Event Detection From Podcasts With People Who Stutter](https://mlsanity.com/paper/2102.12394/) (2021)
- [KSoF: The Kassel State of Fluency Dataset -- A Therapy Centered Dataset of Stuttering](https://mlsanity.com/paper/2203.05383/) (2022)

## Built on by (most cited first, 9 of 9)

- [A Stutter Seldom Comes Alone -- Cross-Corpus Stuttering Detection as a Multi-label Problem](https://mlsanity.com/paper/2305.19255/) (2023)
- [FairSSD: Understanding Bias in Synthetic Speech Detectors](https://mlsanity.com/paper/2404.10989/) (2024)
- [Large Language Models for Dysfluency Detection in Stuttered Speech](https://mlsanity.com/paper/2406.11025/) (2024)
- [Whisper in Focus: Enhancing Stuttered Speech Classification with Encoder Layer Optimization](https://mlsanity.com/paper/2311.05203/) (2023)
- [Boli: A dataset for understanding stuttering experience and analyzing stuttered speech](https://mlsanity.com/paper/2501.15877/) (2025)
- [Optimizing Multi-Stuttered Speech Classification: Leveraging Whisper's Encoder for Efficient Parameter Reduction in Automated Assessment](https://mlsanity.com/paper/2406.05784/) (2024)
- [Multilingual Stutter Event Detection for English, German, and Mandarin Speech](https://mlsanity.com/paper/2603.26939/) (2026)
- [Virtual Speech Therapist: A Clinician-in-the-Loop AI Speech Therapy Agent for Personalized and Supervised Therapy](https://mlsanity.com/paper/2605.01101/) (2026)
- [A Semi-Supervised Framework for Speech Confidence Detection using Whisper](https://mlsanity.com/paper/2605.12387/) (2026)

## Abstract (arXiv)

This paper empirically investigates the influence of different data splits and splitting strategies on the performance of dysfluency detection systems. For this, we perform experiments using wav2vec 2.0 models with a classification head as well as support vector machines (SVM) in conjunction with the features extracted from the wav2vec 2.0 model to detect dysfluencies. We train and evaluate the systems with different non-speaker-exclusive and speaker-exclusive splits of the Stuttering Events in Podcasts (SEP-28k) dataset to shed some light on the variability of results w.r.t. to the partition method used. Furthermore, we show that the SEP-28k dataset is dominated by only a few speakers, making it difficult to evaluate. To remedy this problem, we created SEP-28k-Extended (SEP-28k-E), containing semi-automatically generated speaker and gender information for the SEP-28k corpus, and suggest different data splits, each useful for evaluating other aspects of methods for dysfluency detection.