Picture for Mojtaba Heydari

Mojtaba Heydari

ImmerseDiffusion: A Generative Spatial Audio Latent Diffusion Model

Add code
Oct 19, 2024
Viaarxiv icon

SingFake: Singing Voice Deepfake Detection

Add code
Sep 14, 2023
Viaarxiv icon

SingNet: A Real-time Singing Voice Beat and Downbeat Tracking System

Add code
Jun 04, 2023
Viaarxiv icon

Singing Beat Tracking With Self-supervised Front-end and Linear Transformers

Add code
Aug 31, 2022
Figure 1 for Singing Beat Tracking With Self-supervised Front-end and Linear Transformers
Figure 2 for Singing Beat Tracking With Self-supervised Front-end and Linear Transformers
Figure 3 for Singing Beat Tracking With Self-supervised Front-end and Linear Transformers
Figure 4 for Singing Beat Tracking With Self-supervised Front-end and Linear Transformers
Viaarxiv icon

A Novel 1D State Space for Efficient Music Rhythmic Analysis

Add code
Nov 01, 2021
Figure 1 for A Novel 1D State Space for Efficient Music Rhythmic Analysis
Figure 2 for A Novel 1D State Space for Efficient Music Rhythmic Analysis
Viaarxiv icon

Learning Sparse Analytic Filters for Piano Transcription

Add code
Aug 23, 2021
Figure 1 for Learning Sparse Analytic Filters for Piano Transcription
Figure 2 for Learning Sparse Analytic Filters for Piano Transcription
Figure 3 for Learning Sparse Analytic Filters for Piano Transcription
Figure 4 for Learning Sparse Analytic Filters for Piano Transcription
Viaarxiv icon

BeatNet: CRNN and Particle Filtering for Online Joint Beat Downbeat and Meter Tracking

Add code
Aug 08, 2021
Figure 1 for BeatNet: CRNN and Particle Filtering for Online Joint Beat Downbeat and Meter Tracking
Figure 2 for BeatNet: CRNN and Particle Filtering for Online Joint Beat Downbeat and Meter Tracking
Figure 3 for BeatNet: CRNN and Particle Filtering for Online Joint Beat Downbeat and Meter Tracking
Figure 4 for BeatNet: CRNN and Particle Filtering for Online Joint Beat Downbeat and Meter Tracking
Viaarxiv icon