TY - GEN
T1 - Depthwise Separable Convolutions Versus Recurrent Neural Networks for Monaural Singing Voice Separation
AU - Pyykkönen, Pyry
AU - Mimilakis, Stylianos I.
AU - Drossos, Konstantinos
AU - Virtanen, Tuomas
N1 - jufoid=70574
PY - 2020
Y1 - 2020
N2 - Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neural networks for sequence processing, they are known to have specific difficulties in training and parallelization, especially for the typically long sequences encountered in music source separation. In this paper we present a use-case of replacing RNNs with depth-wise separable (DWS) convolutions, which are a lightweight and faster variant of the typical convolutions. We focus on singing voice separation, employing an RNN architecture, and we replace the RNNs with DWS convolutions (DWS-CNNs). We conduct an ablation study and examine the effect of the number of channels and layers of DWS-CNNs on the source separation performance, by utilizing the standard metrics of signal-to-artifacts, signal-to-interference, and signal-to-distortion ratio. Our results show that by replacing RNNs with DWS-CNNs yields an improvement of 1.20, 0.06, 0.37 dB, respectively, while using only 20.57% of the amount of parameters of the RNN architecture.
AB - Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neural networks for sequence processing, they are known to have specific difficulties in training and parallelization, especially for the typically long sequences encountered in music source separation. In this paper we present a use-case of replacing RNNs with depth-wise separable (DWS) convolutions, which are a lightweight and faster variant of the typical convolutions. We focus on singing voice separation, employing an RNN architecture, and we replace the RNNs with DWS convolutions (DWS-CNNs). We conduct an ablation study and examine the effect of the number of channels and layers of DWS-CNNs on the source separation performance, by utilizing the standard metrics of signal-to-artifacts, signal-to-interference, and signal-to-distortion ratio. Our results show that by replacing RNNs with DWS-CNNs yields an improvement of 1.20, 0.06, 0.37 dB, respectively, while using only 20.57% of the amount of parameters of the RNN architecture.
UR - https://github.com/pppyykknen/mad-twinnet
U2 - 10.1109/MMSP48831.2020.9287169
DO - 10.1109/MMSP48831.2020.9287169
M3 - Conference contribution
T3 - IEEE International Workshop on Multimedia Signal Processing
BT - IEEE International Workshop on Multimedia Signal Processing (MMSP)
T2 - IEEE International Workshop on Multimedia Signal Processing
Y2 - 1 January 1900
ER -