Download full-text PDF

Source
http://dx.doi.org/10.1121/1.1912590DOI Listing

Publication Analysis

Top Keywords

masking noise
4
noise speech-envelope
4
speech-envelope characteristics
4
characteristics studying
4
studying intelligibility
4
masking
1
speech-envelope
1
characteristics
1
studying
1
intelligibility
1

Similar Publications

Robustly detecting mpox and non-mpox using a deep learning framework based on image inpainting.

Sci Rep

January 2025

School of Mathematics and Systems Science, Guangdong Polytechnic Normal University, No. 293, Zhongshan Avenue West, Tianhe District, Guangzhou, 510665, China.

Due to the lack of efficient mpox diagnostic technology, mpox cases continue to increase. Recently, the great potential of deep learning models in detecting mpox and non-mpox has been proven. However, existing methods are susceptible to interference from various noises in real-world settings, require diverse non-mpox images, and fail to detect abnormal input, which makes them unsuitable for practical deployment and application.

View Article and Find Full Text PDF

Background: Tinnitus refers to a common disorder affecting older adults frequently. This condition can disturb mental health and psychological well-being and contribute to cognitive decline. Despite recent advances in research, its pathophysiology remains incompletely understood.

View Article and Find Full Text PDF

Objectives: The SARS-CoV-2 pandemic required the use of personal protective equipment (PPE) in medical and social contexts to reduce exposure and prevent pathogen transmission. This study aims to analyse possible changes in voice and speech parameters with and without PPE.

Methods: Speech samples using different types of PPE were obtained.

View Article and Find Full Text PDF

In real-world scenarios, mixture models are frequently employed to fit complex data, demonstrating remarkable flexibility and efficacy. This paper introduces an innovative Pufferfish privacy algorithm based on Gaussian priors, specifically designed for Gaussian mixture models. By leveraging a sophisticated masking mechanism, the algorithm effectively safeguards data privacy.

View Article and Find Full Text PDF

Harnessing unlabeled data: Enhanced rare earth component content prediction based on BiLSTM-Deep autoencoder.

ISA Trans

January 2025

School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang, 330013, Jiangxi, China; Key Laboratory of Advanced Control & Optimization of Jiangxi Province, Nanchang, 330013, Jiangxi, China. Electronic address:

Traditional data-driven models for predicting rare earth component content are primarily developed by relying on supervised learning methods, which suffer from limitations such as a lack of labeled data, lagging, and poor usage of a major amount of unlabeled data. This paper proposes a novel prediction approach based on the BiLSTM-Deep autoencoder enhanced traditional LSSVM algorithm, termed BiLSTM-DeepAE-LSSVM. This approach thoroughly exploits the implicit information contained in copious amounts of unlabeled data in the rare earth production process, thereby improving the traditional supervised prediction method and increasing the accuracy of component content predictions.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!