Search Results (5)

Stuttering, a prevalent neurodevelopmental disorder, profoundly affects fluent speech, causing involuntary interruptions and recurrent sound patterns. This study addresses the critical need for the accurate classification of stuttering types. The researchers introduce “TranStutter”, a pioneering Convolution-free Transformer-based DL model, designed to excel in speech disfluency classification. Unlike conventional methods, TranStutter leverages Multi-Head Self-Attention and Positional Encoding to capture intricate temporal patterns, yielding superior accuracy. In this study, the researchers employed two benchmark datasets: the Stuttering Events in Podcasts Dataset (SEP-28k) and the FluencyBank Interview Subset. SEP-28k comprises 28,177 audio clips from podcasts, meticulously annotated into distinct dysfluent and non-dysfluent labels, including Block (BL), Prolongation (PR), Sound Repetition (SR), Word Repetition (WR), and Interjection (IJ). The FluencyBank subset encompasses 4144 audio clips from 32 People Who Stutter (PWS), providing a diverse set of speech samples. TranStutter’s performance was assessed rigorously. On SEP-28k, the model achieved an impressive accuracy of 88.1%. Furthermore, on the FluencyBank dataset, TranStutter demonstrated its efficacy with an accuracy of 80.6%. These results highlight TranStutter’s significant potential in revolutionizing the diagnosis and treatment of stuttering, thereby contributing to the evolving landscape of speech pathology and neurodevelopmental research. The innovative integration of Multi-Head Self-Attention and Positional Encoding distinguishes TranStutter, enabling it to discern nuanced disfluencies with unparalleled precision. This novel approach represents a substantial leap forward in the field of speech pathology, promising more accurate diagnostics and targeted interventions for individuals with stuttering disorders. Full article

This work deals with automatically detecting stuttering and its subclasses. An effective classification of stuttering along with its subclasses could find wide application in determining the severity of stuttering by speech therapists, preliminary patient diagnosis, and enabling communication with the previously mentioned voice assistants. The first part of this work provides an overview of examples of classical and deep learning methods used in automated stuttering classifications as well as databases and features used. Then, two classical algorithms (k-NN (k-nearest neighbor) and SVM (support vector machine) and several deep models (ConvLSTM; ResNetBiLstm; ResNet18; Wav2Vec2) are examined on the available stuttering dataset. The experiments investigate the influence of individual signal features such as Mel-Frequency Cepstral Coefficients (MFCCs), pitch-determining features in the signal, and various 2D speech representations on the classification results. The most successful algorithm, i.e., ResNet18, can classify speech disorders at the F1 measure of 0.93 for the general class. Additionally, deep learning shows superiority over a classical approach to stuttering disorder detection. However, due to insufficient data and the quality of the annotations, the results differ between stuttering subcategories. Observation of the impact of the number of dense layers, the amount of data in the training set, and the amount of data divided into the training and test sets on the effectiveness of stuttering event detection is provided for further use of this methodology. Full article

In this paper, utilising real-internet traffic data, we modified a popular network emulator to better imitate real network traffic and studied its subjective and objective implications on QoE for cloud-gaming apps. Subjective QoE evaluation was then used to compare cross-correlated QoS metric with the default non-correlated emulator setup. Human test subjects showed different correlated versus non-correlated QoS parameters affects regarding cloud gaming QoE. Game-QoE is influenced more by network degradation than video QoE. To validate our subjective QoE study, we analysed the experiment’s video objectively. We tested how well Full-Reference VQA measures subjective QoE. The correlation between FR QoE and subjective MOS was greater in non-correlated QoS than in correlated QoS conditions. We also found that correlated scenarios had more stuttering events compared to non-correlated scenarios, resulting in lower game QoE. Full article

A 5-year-old recently castrated male Doberman dog presented for prolonged erection of one week’s duration with associated pain and dysuria. This was the fourth episode within a year. Each episode was associated with an unusual event, which was stressful for the dog. Castration performed two months prior to the final episode did not prevent recurrence. Due to tissue necrosis, penile amputation and urethrostomy had to be performed. The dog recovered fully. Prolonged erection that persists beyond or that is unrelated to sexual stimulation is called “priapism”. This term refers to the Greek god Priapus, a god of fertility, memorialized in sculptures for his giant phallus. In humans, depending on the mechanism involved, priapism is classified as nonischemic or ischemic. Because prognosis and treatment are different, priapism must be determined to be nonischemic or ischemic. Nonischemic priapism is a rare condition observed when an increase in penile arterial blood flow overwhelms the capacity of venous drainage; it is often associated with penile trauma, and does not require medical intervention. Ischemic priapism is associated with decreased venous return. In humans, ischemic priapism accounts for 95% of cases, the majority of which are idiopathic. Ischemic priapism is a urological emergency; simple conservative measures such as aspiration of blood from the corpora cavernosa and intracavernosal injection of an adrenergic agent are often successful. Stuttering priapism, also called recurrent or intermittent priapism, is a particular form of ischemic priapism reported in humans that is characterized by repetitive episodes of prolonged erections. Management consists of treating each new episode as an episode of acute ischemic priapism, and preventing recurrence with oral medications such as dutasteride and/or baclofen, gabapentin, or tadalafil. To the authors’ knowledge, this case is the first report of stuttering priapism in a dog. Full article

Pandemics are a consequence of a series of processes that span scales from viral biology at 10⁻⁹ m to global transmission at 10⁶ m. The pathogen passes from one host species to another through a sequence of events that starts with an infected reservoir host and entails interspecific contact, innate immune responses, receptor protein structure within the potential host, and the global spread of the novel pathogen through the naive host population. Each event presents a potential barrier to the onward passage of the virus and should be characterized with an integrated transdisciplinary approach. Epidemic control is based on the prevention of exposure, infection, and disease. However, the ultimate pandemic prevention is prevention of the spillover event itself. Here, we focus on the potential for preventing the spillover of henipaviruses, a group of viruses derived from bats that frequently cross species barriers, incur high human mortality, and are transmitted among humans via stuttering chains. We outline the transdisciplinary approach needed to prevent the spillover process and, therefore, future pandemics. Full article