首页|Jilin Normal University Reports Findings in Robotics (3 directional Inception-ResUNet: Deep spatial feature learning for multichannel singing voice separation with distortion)
Jilin Normal University Reports Findings in Robotics (3 directional Inception-ResUNet: Deep spatial feature learning for multichannel singing voice separation with distortion)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Public Library Science
New research on Robotics is the subject of a report. According to news originating from Jilin, People's Republic of China, by NewsRx correspondents, research stated, “Singing voice separation on robots faces the problem of interpreting ambiguous auditory signals. The acoustic signal, which the humanoid robot perceives through its onboard microphones, is a mixture of singing voice, music, and noise, with distortion, attenuation, and reverberation.” Financial support for this research came from China University Industry, University and Research Innovation Fund. Our news journalists obtained a quote from the research from Jilin Normal University, “In this paper, we used the 3D Inception-ResUNet structure in the U-shaped encoding and decoding network to improve the utilization of the spatial and spectral information of the spectrogram. Multiobjectives were used to train the model: magnitude consistency loss, phase consistency loss, and magnitude correlation consistency loss. We recorded the singing voice and accompaniment derived from the MIR-1K dataset with NAO robots and synthesized the 10-channel dataset for training the model.” According to the news editors, the research concluded: “The experimental results show that the proposed model trained by multiple objectives reaches an average NSDR of 11.55 dB on the test dataset, which outperforms the comparison model.”
JilinPeople's Republic of ChinaAsiaEmerging TechnologiesMachine LearningNano-robotRobotics
NETL
NSTL
Public Library Science
