The Influence of Dataset Partitioning on Dysfluency Detection Systems
- 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.
| Author: | Sebastian P. BayerlORCiD, Dominik Wagner, Elmar NöthORCiD, Tobias BockletORCiD, Korbinian RiedhammerORCiD |
|---|---|
| DOI: | https://doi.org/10.1007/978-3-031-16270-1_35 |
| ISBN: | 9783031162695 |
| ISSN: | 0302-9743 |
| Parent Title (English): | Text, Speech, and Dialogue |
| Publisher: | Springer International Publishing |
| Place of publication: | Cham |
| Document Type: | Part of a Book |
| Language: | English |
| Date of first Publication: | 2022/09/16 |
| Reviewed: | Begutachtet/Reviewed |
| Release Date: | 2024/08/01 |
| Tag: | Computer Science; Informatics |
| Pagenumber: | 14 |
| First Page: | 423 |
| Last Page: | 436 |
| Konferenzangabe: | 25th International Conference, TSD 2022, Brno, Czech Republic, September 6–9, 2022 |
| institutes: | Fakultät Informatik |
| Zentrum für Künstliche Intelligenz (KIZ) | |
| Research Themes: | Digitalisierung & Künstliche Intelligenz |
