Semiconductor Engineering

Accelerating Semiconductor Innovation Through Machine Learning-Driven Modeling

Using AI and machine learning as transformative solutions for semiconductor device modeling and parameter extraction.

Kolmogorov-Arnold networks bridge AI and scientific discovery by increasing interpretability

AI has successfully been applied in many areas of science, advancing technologies like weather prediction and protein folding ...
eLife

High-Fidelity Neural Speech Reconstruction through an Efficient Acoustic-Linguistic Dual-Pathway Framework

This study presents a valuable advance in reconstructing naturalistic speech from intracranial ECoG data using a dual-pathway model. The evidence supporting the claims of the authors is solid, ...
Scientific Research Publishing

Kong, J., Kim, J. and Bae, J. (2020) HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis.

ABSTRACT: The aim of this research is to develop a speech synthesis model tailored towards Nigerian languages by leveraging natural language processing tool such as FastSpeech 2 and meta-tts for ...
GitHub

Generative Neural Network Based Image Compression

Traditional lossy compression algorithms like JPEG are not data-specific and may not achieve the best possible compression rates for datasets where images are semantically related. This project ...
IEEE

QHARMA-GAN: Quasi-Harmonic Neural Vocoder Based on Autoregressive Moving Average Model

Abstract: Vocoders, encoding speech signals into acoustic features and allowing for speech signal reconstruction from them, have been studied for decades. Recently, the rise of deep learning has ...
IEEE

Is GAN Necessary for Mel-Spectrogram-Based Neural Vocoder?

Recently, mainstream mel-spectrogram-based neural vocoders rely on generative adversarial network (GAN) for high-fidelity speech generation, e.g., HiFi-GAN and BigVGAN. However, the use of GAN ...
Electronic Specifier

How Renesas is capitalising on Edge AI and GaN

The new series of MCUs, the RA8P1 group, are specifically targeted at AI, ML, and real-time analytics applications. Thanks to TinyML models, devices that are more constrained both in terms of board ...
Electronic Design

Scaling AI Data Center Power Delivery with Si, SiC, and GaN

Large language models (LLMs) and other neural networks draw substantial power when processing complex artificial-intelligence (AI) and machine-learning (ML) workloads. Designed for traditional server ...