Automatic speech disfluency detection using wav2vec2. 0 for different languages with variable lengths

J Liu, A Wumaier, D Wei, S Guo - Applied Sciences, 2023 - mdpi.com
Speech is critical for interpersonal communication, but not everyone has fluent
communication skills. Speech disfluency, including stuttering and interruptions, affects not …

Efficient stuttering event detection using siamese networks

P Mohapatra, B Islam, MT Islam… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
Speech disfluency research is pivotal to accommodating atypical speakers in mainstream
conversational technology. However, the lack of publicly available labeled and unlabeled …

Sequence-based data-constrained deep learning framework to predict spider dragline mechanical properties

A Pandey, W Chen, S Keten - Communications Materials, 2024 - nature.com
Spider dragline silk is known for its exceptional strength and toughness; hence
understanding the link between its primary sequence and mechanics is crucial. Here, we …

[HTML][HTML] A novel attention model across heterogeneous features for stuttering event detection

AK Al-Banna, H Fang, E Edirisinghe - Expert Systems with Applications, 2024 - Elsevier
Stuttering is a prevalent speech disorder affecting millions worldwide. To provide an
automatic and objective stuttering assessment tool, Stuttering Event Detection (SED) is …

Whisper in Focus: Enhancing Stuttered Speech Classification with Encoder Layer Optimization

H Ameer, S Latif, R Latif, S Mukhtar - arXiv preprint arXiv:2311.05203, 2023 - arxiv.org
In recent years, advancements in the field of speech processing have led to cutting-edge
deep learning algorithms with immense potential for real-world applications. The automated …

Dysfluencies Seldom Come Alone--Detection as a Multi-Label Problem

SP Bayerl, D Wagner, F Hönig, T Bocklet… - arXiv preprint arXiv …, 2022 - arxiv.org
Specially adapted speech recognition models are necessary to handle stuttered speech. For
these to be used in a targeted manner, stuttered speech must be reliably detected. Recent …

Phase-driven Domain Generalizable Learning for Nonstationary Time Series

P Mohapatra, L Wang, Q Zhu - arXiv preprint arXiv:2402.05960, 2024 - arxiv.org
Monitoring and recognizing patterns in continuous sensing data is crucial for many practical
applications. These real-world time-series data are often nonstationary, characterized by …

Missingness-resilient Video-enhanced Multimodal Disfluency Detection

P Mohapatra, S Likhite, S Biswas, B Islam… - arXiv preprint arXiv …, 2024 - arxiv.org
Most existing speech disfluency detection techniques only rely upon acoustic data. In this
work, we present a practical multimodal disfluency detection approach that leverages …

A Stutter Seldom Comes Alone--Cross-Corpus Stuttering Detection as a Multi-label Problem

SP Bayerl, D Wagner, I Baumann, F Hönig… - arXiv preprint arXiv …, 2023 - arxiv.org
Most stuttering detection and classification research has viewed stuttering as a multi-class
classification problem or a binary detection task for each dysfluency type; however, this does …

Optimizing Multi-Stuttered Speech Classification: Leveraging Whisper's Encoder for Efficient Parameter Reduction in Automated Assessment

H Ameer, S Latif, R Latif - arXiv preprint arXiv:2406.05784, 2024 - arxiv.org
The automated classification of stuttered speech has significant implications for timely
assessments providing assistance to speech language pathologists. Despite notable …