Applications in music and audio processing

Stochastic Optimization of Vector Quantization Methods in Application to Speech and Image Processing

Sinusoidal Frequency Estimation by Gradient Descent

Deep architecture for doa trajectory localization.

Full-band General Audio Synthesis with Score-based Diffusion

CNEG-VC: Contrastive Learning using Hard Negative Example in Non-parallel Voice Conversion

MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separation

ESTIMATION OF TIME-VARYING GRAPH TOPOLOGIES FROM GRAPH SIGNALS

Blind Estimation of Audio Processing Graph

Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models

Anomalous Sound Detection using Audio Representation with Machine ID based Contrastive Learning Pretraining

Framewise multiple sound source localization and counting using binaural spatial audio signals

An improved optimal transport kernel embedding method with gating mechanism for singing voice separation and speaker identification