☆ 4.5 Article

Dysarthria Speech Detection Using Convolutional Neural Networks with Gated Recurrent Unit

HEALTHCARE (2022)

Related references

Note: Only part of the references are listed.

Article Engineering, Biomedical

Voice disorder classification using speech enhancement and deep learning models

Mounira Chaiani et al.

Summary: This paper proposes a two-stage framework for accurately classifying different voice pathologies. The first stage involves speech enhancement processing that treats impaired voice as a noisy signal, using the noise lestral harmonic-to-noise ratio (CHNR). The second stage utilizes a convolutional neural network with long short-term memory (CNN-LSTM) architecture to learn complex features from spectrograms of the enhanced signals in the first stage. Experimental results show that using the minimum mean square error (MMSE) based signal enhancer and the sinusoidal rectified unit (SinRU) as the activation function improves the automatic classification of voice pathologies and dysarthria severity levels.

BIOCYBERNETICS AND BIOMEDICAL ENGINEERING (2022)

Add to Collection

Article Telecommunications

Dysarthric Speech Recognition Using Variational Mode Decomposition and Convolutional Neural Networks

R. Rajeswari et al.

Summary: The researchers enhanced dysarthric speech using variational mode decomposition and wavelet thresholding, and then trained convolutional neural networks to generate a model supporting dysarthric speech recognition. Evaluation on the UA-Speech database showed that the proposed method achieved higher accuracy compared to existing methods.

WIRELESS PERSONAL COMMUNICATIONS (2022)

Add to Collection

Article Engineering, Biomedical

Classification of ALS patients based on acoustic analysis of sustained vowel phonations

M. Vashkevich et al.

Summary: The study focuses on analyzing the sustained phonation of vowels /a/ and /i/ to classify ALS patients automatically, using a range of acoustic features. The experiments show that the LDA model based on 32 features selected by LASSO algorithm achieves high accuracy, while a simpler LDA model with 5 features also shows good performance.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2021)

Add to Collection

Article Computer Science, Information Systems

Deep Learning Techniques for Android Botnet Detection

Suleiman Y. Yerima et al.

Summary: Android, the most popular mobile operating system worldwide, is facing increasing malware threats, leading to the need for more effective detection methods. Deep learning has gained attention as a machine learning approach to enhance Android botnet detection. This paper presents a comparative study of deep learning techniques for Android botnet detection, achieving state-of-the-art results based on the ISCX botnet dataset and outperforming classical machine learning classifiers.

ELECTRONICS (2021)

Add to Collection

Article Engineering, Biomedical

Parkinson disease prediction using intrinsic mode function based features from speech signal

Biswajit Karan et al.

BIOCYBERNETICS AND BIOMEDICAL ENGINEERING (2020)

Add to Collection

Article Computer Science, Information Systems

Glottal Source Information for Pathological Voice Detection

N. P. Narendra et al.

IEEE ACCESS (2020)

Add to Collection

Article Acoustics

Dysarthric speech classification from coded telephone speech using glottal features

N. P. Narendra et al.

SPEECH COMMUNICATION (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Analysis of speaker recognition methodologies and the influence of kinetic changes to automatically detect Parkinson's Disease

Laureano Moro-Velazquez et al.

APPLIED SOFT COMPUTING (2018)

Add to Collection

Article Engineering, Biomedical

Voice pathology detection using interlaced derivative pattern on glottal source excitation

Ghulam Muhammad et al.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2017)

Add to Collection

Article Medicine, Research & Experimental

Voice problems and depression among adults in the United States

Schelomo Marmor et al.

LARYNGOSCOPE (2016)

Add to Collection

Review Clinical Neurology

When the word doesn't come out: A synthetic overview of dysarthria

Liborio Rampello et al.

JOURNAL OF THE NEUROLOGICAL SCIENCES (2016)

Add to Collection

Article Audiology & Speech-Language Pathology

A Demonstration of Improved Precision of Word Recognition Scores

Robert S. Schlauch et al.

JOURNAL OF SPEECH LANGUAGE AND HEARING RESEARCH (2014)

Add to Collection

Article Audiology & Speech-Language Pathology

Speech technology-based assessment of phoneme intelligibility in dysarthria

Gwen Van Nuffelen et al.

INTERNATIONAL JOURNAL OF LANGUAGE & COMMUNICATION DISORDERS (2009)

Add to Collection

Article Computer Science, Artificial Intelligence

An introduction to ROC analysis

Tom Fawcett

PATTERN RECOGNITION LETTERS (2006)

Add to Collection

Article Computer Science, Artificial Intelligence

LSTM recurrent networks learn simple context-free and context-sensitive languages

FA Gers et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS (2001)

Add to Collection

© Peeref 2019-2024. All rights reserved.