In this paper, we study wireless broadcast schemes based on online fountain codes. We first propose and analyze an online fountain code based-broadcast scheme, where the coded symbol degree is updated based on the decoding states of all receivers. Then we propose and analyze an improved broadcast scheme by taking advantage of the received coded symbols that are not immediately decodable. Simulation results demonstrate that our proposed scheme has better performance compared to other broadcast schemes based on feedback fountain codes.
In this paper, a self-supervised learning pre-trained model is proposed and successfully applied in language identification task (LID). A Transformer encoder is employed and multi-task strategy is used to train the self-supervised model: the first task is to reconstruct the masking spans of input frames and the second task is a supervision task where the phoneme and phonological labels are used with Connectionist Temporal Classification (CTC) loss. By using this multi-task learning loss, the model is expected to capture high-level speech representation in phonological space. Meanwhile, an adaptive loss is also applied for multi-task learning to balance the weight between different tasks. After the pretraining stage, the self-supervised model is used for xvector systems. Our LID experiments are carried out on the oriental language recognition (OLR) challenge data corpus and 1 s, 3 s, Full-length test sets are selected. Experimental results show that on 1 s test set, feature extraction model approach can get best performance and in 3 s, Full-length test, the fine-tuning approach can reach the best performance. Furthermore, our results prove that the multi-task training strategy is effective and the proposed model can get the best performance.
In advanced transportation-management systems, variable speed limits are a crucial application. Deep reinforcement learning methods have been shown to have superior performance in many applications, as they are an effective approach to learning environment dynamics for decision-making and control. However, they face two significant difficulties in traffic-control applications: reward engineering with delayed reward and brittle convergence properties with gradient descent. To address these challenges, evolutionary strategies are well suited as a class of black-box optimization techniques inspired by natural evolution. Additionally, the traditional deep reinforcement learning framework struggles to handle the delayed reward setting. This paper proposes a novel approach using covariance matrix adaptation evolution strategy (CMA-ES), a gradient-free global optimization method, to handle the task of multi-lane differential variable speed limit control. The proposed method uses a deep-learning-based method to dynamically learn optimal and distinct speed limits among lanes. The parameters of the neural network are sampled using a multivariate normal distribution, and the dependencies between the variables are represented by a covariance matrix that is optimized dynamically by CMA-ES based on the freeway’s throughput. The proposed approach is tested on a freeway with simulated recurrent bottlenecks, and the experimental results show that it outperforms deep reinforcement learning-based approaches, traditional evolutionary search methods, and the no-control scenario. Our proposed method demonstrates a 23% improvement in average travel time and an average of a 4% improvement in CO, HC, and NOx emission.Furthermore, the proposed method produces explainable speed limits and has desirable generalization power.
This paper proposes a novel microphone array speech denoising scheme based on tensor filtering methods including truncated HOSVD (High-Order Singular Value Decomposition), low rank tensor approximation and multi-mode Wiener filtering. Microphone array speech signal is represented in three-order tensor space with channel, time, and spectrum modes and then tensor filtering model can be designed to process the multiway array data. As to the first method, noise can be reduced through the truncated HOSVD which is a simple scheme in tensor processing. It is more accurate to find the lower-rank approximation of the three-order tensor with Tucker model. Then MDL (Minimum Description Length) criterion is used to estimate the optimal tensor rank in the second method. Further, multimode Wiener filtering approach upon tensor analysis can be considered as the spanning of one-mode wiener filtering. How to take advantages of tensor model to obtain a set of filters is the heart of the novel scheme. The performances of the proposed three approaches are evaluated with objective indexes and listening quality test. The experimental results indicate that the proposed tenor filtering methods have potential ability of retrieving the target signal from noisy microphone array signal and the multi-mode Wiener filtering method provides the best denoising results among the three ones.
With the increasing demand for high quality audio, stereo audio coding has become more and more important. In this paper, a multi-frame coding method based on Principal Component Analysis (PCA) is proposed for the compression of audio signals, including both mono and stereo signals. The PCA-based method makes the input audio spectral coefficients into eigenvectors of covariance matrices and reduces coding bitrate by grouping such eigenvectors into fewer number of vectors. The multi-frame joint technique makes the PCA-based method more efficient and feasible. This paper also proposes a quantization method that utilizes Pyramid Vector Quantization (PVQ) to quantize the PCA matrices proposed in this paper with few bits. Parametric coding algorithms are also employed with PCA to ensure the high efficiency of the proposed audio codec. Subjective listening tests with Multiple Stimuli with Hidden Reference and Anchor (MUSHRA) have shown that the proposed PCA-based coding method is efficient at processing stereo audio.