마바폴리: 선별적 상태 공간 모델을 이용한 폴리 사운드 생성
선별적 상태 공간 모델인 마바를 활용하여 폴리 사운드를 생성하는 모델 MambaFoley를 제안한다.
Efficient Backpropagation for Time-Varying All-Pole Filters in Differentiable Audio Systems
This paper proposes an efficient backpropagation algorithm and implementation for time-varying all-pole filters that can be used to model various analog audio systems end-to-end using gradient descent.
Extending Non-Negative Matrix Factorization to Irregularly-Sampled Time-Frequency Representations using Implicit Neural Representations
Non-negative matrix factorization (NMF) can be extended to irregularly-sampled time-frequency representations by formulating it in terms of continuous functions instead of fixed vectors, enabling the use of implicit neural representations to model the underlying basis templates and activations.
ASiT: Local-Global Audio Spectrogram Vision Transformer for Event Classification
Transformers are effective for audio tasks with self-supervised pretraining, enhancing performance across various classification tasks.
ASiT: Local-Global Audio Spectrogram Vision Transformer for Event Classification
Transformers are adapted for audio tasks through self-supervised pretraining, enhancing performance in various classification tasks.
© 2024 by Linnk AI