paper-with-me

홈 › Papers

Investigating U-Nets with various Intermediate Blocks for Spectrogram-based Singing Voice Separation

2019-12-02 · Woosung Choi, Minseok Kim, Jaehwa Chung, Daewon Lee, Soonyoung Jung

Singing Voice Separation (SVS) tries to separate singing voice from a given mixed musical signal. Recently, many U-Net-based models have been proposed for the SVS task, but there were no existing works that evaluate and compare various types of intermediate blocks that can be used in the U-Net architecture. In this paper, we introduce a variety of intermediate spectrogram transformation blocks. We implement U-nets based on these blocks and train them on complex-valued spectrograms to consider both magnitude and phase. These networks are then compared on the SDR metric. When using a particular block composed of convolutional and fully-connected layers, it achieves state-of-the-art SDR on the MUSDB singing voice separation task by a large margin of 0.9 dB. Our code and models are available online.

📄 PDF Abstract BibTeX arXiv:1912.02591

Code (1)

ws-choi/ISMIR2020_U_Nets_SVS 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis

2020-11-06 · Ron J. Weiss, RJ Skerry-Ryan, Eric Battenberg, Soroosh Mariooryad 외

We describe a sequence-to-sequence neural network which directly generates speech waveforms from text inputs. The architecture extends the Tacotron model by incorporating a normalizing flow into the autoregressive decode…

DecoderSpeech Synthesistext-to-speechText to Speech+1

Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer

2023-09-26 · Xiaofeng Liu, Fangxu Xing, Maureen Stone, Jiachen Zhuo 외

The tongue's intricate 3D structure, comprising localized functional units, plays a crucial role in the production of speech. When measured using tagged MRI, these functional units exhibit cohesive displacements and deri…

Audio Synthesis

Axial Residual Networks for CycleGAN-based Voice Conversion

2021-02-16 · Jaeseong You, Gyuhyeon Nam, Dalhyun Kim, Gyeongsu Chae

We propose a novel architecture and improved training objectives for non-parallel voice conversion. Our proposed CycleGAN-based model performs a shape-preserving transformation directly on a high frequency-resolution mag…

Voice Conversion

Adam-mini: Use Fewer Learning Rates To Gain More

2024-06-24 · Yushun Zhang, Congliang Chen, Ziniu Li, Tian Ding 외

We propose Adam-mini, an optimizer that achieves on par or better performance than AdamW with 50% less memory footprint. Adam-mini reduces memory by cutting down the learning rate resources in Adam (i.e., $1/\sqrt{v}$). …

Optimising for Interpretability: Convolutional Dynamic Alignment Networks

2021-09-27 · Moritz Böhle, Mario Fritz, Bernt Schiele

We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA Nets), which are performant classifiers with a high degree of inherent interpretability. Their core building blocks…