Overview: AI-generated music often sounds too perfect, with a steady pitch, a rigid rhythm, and a lack of human flaws.Repetitive loops, odd textures, and unnatu ...

Abstract: In this paper, we propose a deep learning (DL)-based task-driven spectrum prediction framework, named DeepSPred. The DeepSPred comprises a feature encoder and a task predictor, where the ...

Abstract: This paper addresses the problem of estimating the instantaneous frequency (IF) and amplitude of the modes composing a non-stationary multicomponent signal in the presence of noise. A novel ...

This study proposes a novel heterogeneous stacking ensemble learning model for the fusion of phonocardiogram (PCG) spectrogram texture and deep features to detect heart failure with preserved ejection ...

Diffusion Speech is a diffusion-based text-to-speech model. Our speech synthesis pipeline is quite simple. We use a diffusion transformer model (DiT) to predict the duration of each phoneme. Then we ...

Researchers have just published a study demonstrating that the flying gurnard (Dactylopterus volitans) emits sounds while ...