Recent work has shown the effectiveness of the plug-and-play priors (PnP) framework for regularized image reconstruction. However, the performance of PnP depends on the quality of image denoiser used as a prior. In this letter, we design a novel PnP denoising prior, called multiple self-similarity net (MSSN), based on the recurrent neural network (RNN) with self-similarity matching using multi-head attention mechanism. Unlike traditional neural net denoisers, MSSN exploits different types of relationships among non-local and repeating features to remove the noise in the input image. We numerically evaluate the performance of MSSN as a module within PnP for solving magnetic resonance (MR) image reconstruction. Experimental results show the stable convergence and excellent performance of MSSN for reconstructing images from highly compressive Fourier measurements.

Genre is one of the most widely mentioned music labels which have a great influence on accuracy of music recommendation. Machine learning is often used to tackle with genre classification task, but the result of the approach heavily depends on the performance of feature extraction. Deep neural network automatically learns advanced features layer by layer, which makes excellent results in many areas. Music signal is sequential and Recurrent Neural Network (RNN) is widely employed for sequential data. Among variant units of RNN, Independently Recurrent Neural Network (IndRNN) can learn long-term relationship better than popular units such as Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). In addition, IndRNN has better computational efficiency. Consequently, multi-layer IndRNN is used as the main part of our model to classify music genres on the GTZAN dataset. In order to keep the information loss as less as possible, scattering transform is used to preprocess the raw music data. The experimental results show that the model achieves a competitive result in music genre classification task compared with the state-of-the-art models.

In music information retrieval (MIR), beat tracking is one of the most fundamental tasks. To obtain this critical component from rhythmic music signals, a previous beat tracking system of hidden Markov model (HMM) with a recurrent neural network (RNN) observer was developed. Although the frequency of music beat is quite stable, existing HMM based methods do not take this feature into account. Accordingly, most of hidden states in these HMM-based methods are redundant, which is a disadvantage for time efficiency. In this paper, we proposed an efficient HMM using hidden states by exploiting the frequency contents of the neural network’s observation with Fourier transform, which extremely reduces the computational complexity. Observers that previous works used, such as bi-directional recurrent neural network (Bi-RNN) and temporal convolutional network (TCN), cannot perceive the frequency of music beat. To obtain more reliable frequencies from music, a periodic recurrent neural network (PRNN) based on attention mechanism is proposed as well, which is used as the observer in HMM. Experimental results on open source music datasets, such as GTZAN, Hainsworth, SMC, and Ballroom, show that our efficient HMM with PRNN is competitive to the state-of-the-art methods and has lower computational cost.