Tech Xplore

Human brain and AI speech recognition decode speech in similar step-by-step stages, study finds

Over the past decades, computer scientists have developed numerous artificial intelligence (AI) systems that can process human speech in different languages. The extent to which these models replicate ...

How post-stroke aphasia disrupts fluent speech

A study led by a speech neuroscientist at The University of Texas at Dallas sheds light on how damage from stroke disrupts the brain mechanisms required for fluent speech. The research, published in ...
Tech Xplore

Can people distinguish between AI-generated and human speech?

In a collaboration between Tianjin University and the Chinese University of Hong Kong, researchers led by Xiangbin Teng used behavioral and brain activity measures to explore whether people can ...
Scientific Research Publishing

Cybersecurity and Forensic Audio Analysis: Deepfake Detection Based on Mfcc, Audio-Text Disconsistency, and Prosodic Features ()

1 Department of Computer and Instructional Technologies Education, Gazi Faculty of Education, Gazi University, Ankara, Türkiye. 2 Department of Forensic Informatics, Institute of Informatics, Gazi ...
IEEE

RRAM-Based Spectral-Domain Convolution Accelerator for Reliable and Energy-Efficient CNN Inference

Abstract: The growing computational demands of convolutional neural networks (CNNs) have motivated the use of spectral-domain inference as an alternative to costly spatial-domain convolutions. In this ...
IEEE

Speech Emotion Recognition using Branched-based Convolutional Neural Network Technique

Abstract: Speech Emotion Recognition is a significant pattern recognition of human speech using feature extraction for communication media. This paper aims to recognize speech emotion through the CNN ...
IEEE

Using Convolutional Neural Networks for Image Recognition in IoT Applications

Abstract: Convolutional Neural Networks (CNNs) have grown into a powerful picture identification tool. They are an important part of making Internet of Things (IoT) apps. In this regard, CNNs make it ...
IEEE

DASC: A DRAM Data Mapping Methodology for Sparse Convolutional Neural Networks

Abstract: The data transferring of sheer model size of CNN (Convolution Neural Network) has become one of the main performance challenges in modern intelligent systems. Although pruning can trim down ...