KSoF: The Kassel State of Fluency Dataset - A Therapy Centered Dataset of Stuttering

@article{Bayerl2022KSoFTK,
  title={KSoF: The Kassel State of Fluency Dataset - A Therapy Centered Dataset of Stuttering},
  author={S.P. Bayerl and Alexander W. von Gudenberg and Florian H{\"o}nig and Elmar N{\"o}th and Korbinian Riedhammer},
  journal={ArXiv},
  year={2022},
  volume={abs/2203.05383}
}
Stuttering is a complex speech disorder that negatively affects an individual’s ability to communicate effectively. Persons who stutter (PWS) often suffer considerably under the condition and seek help through therapy. Fluency shaping is a therapy approach where PWSs learn to modify their speech to help them to overcome their stutter. Mastering such speech techniques takes time and practice, even after therapy. Shortly after therapy, success is evaluated highly, but relapse rates are high. To… 

Figures and Tables from this paper

Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0
Stuttering is a varied speech disorder that harms an individual’s communication ability. Persons who stutter (PWS) often use speech therapy to cope with their condition. Improving speech recognition
Detecting Vocal Fatigue with Neural Embeddings
TLDR
It is shown that vocal fatigue can be reliably predicted using all three kinds of neural embeddings after only 50 minutes of continuous speak-ing when temporal smoothing and normalization are applied to the extractedembeddings.
The Influence of Dataset Partitioning on Dysfluency Detection Systems
TLDR
It is shown that the SEP-28k dataset is dominated by only a few speakers, making it difficult to evaluate, and a new corpus is created, containing semi-automatically generated speaker and gender information for the SEPs corpus, which is useful for evaluating other aspects of methods for dysfluency detection.
The ACM Multimedia 2022 Computational Paralinguistics Challenge: Vocalisations, Stuttering, Activity, & Mosquitoes
TLDR
This work describes the Sub-Challenges, baseline feature extraction, and classifiers based on the ‘usual’ ComParE and BoAW features, the auDeep toolkit, and deep feature extraction from pre-trained CNNs using the DeepSpectrum toolkit and adds end-to-end sequential modelling, and a log-mel-128-BNN.

References

SHOWING 1-10 OF 30 REFERENCES
Towards Automated Assessment of Stuttering and Stuttering Therapy
TLDR
The Speech Control Index (SCI) is introduced, a new method to evaluate the severity of stuttering that can be used to assess therapy success for fluency shaping and both SES and SCI are evaluated on a new comprehensively labeled dataset containing stuttered German speech of clients.
Automatic recognition of children's read speech for stuttering application
TLDR
This study investigates how automatic speech recognition could help clinicians by providing a tool that automatically recognises stuttering events and provides a useful written transcription of what was said and examines the effect of augmenting the language model with artificially generated data.
SEP-28k: A Dataset for Stuttering Event Detection from Podcasts with People Who Stutter
TLDR
This work introduces Stuttering Events in Podcasts (SEP-28k), a dataset containing over 28k clips labeled with five event types including blocks, prolongations, sound repetitions, word repetition, and interjections, and benchmarks a set of acoustic models on SEP- 28k and the public FluencyBank dataset.
FluentNet: End-to-End Detection of Stuttered Speech Disfluencies With Deep Learning
TLDR
This work proposes an end-to-end deep neural network, FluentNet, capable of detecting a number of different stutter types and presents LibriStutter: a stuttered speech dataset based on the public LibriSpeech dataset with synthesized stutters.
Automatic stuttering recognition using hidden Markov models
TLDR
The combination of the work of speech therapists and speech recognition systems is described to evaluate the degree of stuttering during therapy and to use the automatic analysis of stuttered speech as a screening method, e.g. the search for potential stutterers at an early age.
Identification of Primary and Collateral Tracks in Stuttered Speech
TLDR
This work introduces a novel forced-aligned disfluency dataset from a corpus of semi-directed interviews, and presents baseline results directly comparing the performance of text-based features (word and span information) and speech-based (acoustic-prosodic information).
Efficacy of the Modifying Phonation Intervals (MPI) Stuttering Treatment Program With Adults Who Stutter.
TLDR
Modifying Phonation Intervals treatment was relatively more effective at assisting clients to identify and change the specific speech behaviors that are associated with successful treatment of stuttered speech in adults.
Management of stuttering using cognitive behavior therapy and mindfulness meditation
TLDR
Cognitive behavior therapy and mindfulness equip the client with the skills to manage the problems that occur as a result of stuttering, and the chosen therapeutic paradigm must involve booster sessions over a long term.
Computergestützte Therapie bei Redeflussstörungen: Die langfristige Wirksamkeit der Kasseler Stottertherapie (KST)
The Kassel Stuttering Therapy (KST) is a computer-assisted German adaptation of fluency shaping. 400 clients (aged 9-65 years) completed the 2- to 3-week in-patient intensive treatment. Long-term
Detecting Multiple Speech Disfluencies Using a Deep Residual Network with Bidirectional Long Short-Term Memory
TLDR
This work proposes a model that relies solely on acoustic features, allowing for identification of several variations of stutter disfluencies without the need for speech recognition, outperforming the state-of-the-art by almost 27%.
...
...