Topic Detection and Tracking technique (TDT) has been commonly used to identify the hot topics from the huge volume of Internet news information and keep up with the hot news. However, traditional topic detection and tracking methods have shown low accuracy and low efficiency. In this paper, a topic detection system driven by big data is built on the Spark platform, which aims at improving the efficiency of news collecting from the Internet and improving the accuracy and efficiency of topic detection and tracking tasks. This system can be easily employed in a distributed architecture and work as a parallelized news collecting and topic detection system. An improved density-based spatial clustering of application with noise (DBSCAN) clustering algorithm based on the time window is proposed to achieve accurate topic detection with the auxiliary advantage of reducing the time complexity. A parallel KNN based topic tracking algorithm is proposed for the topic tracking task. Experiments including comparison with some baseline algorithms and quantitative and qualitative analyses are conducted on pseudo-distributed Spark platform, which demonstrates the effectiveness and efficiency of the parallelized topic detection system.

Knowledge graph (KG)-based recommendation methods effectively alleviate the data sparsity and cold-start problems in collaborative filtering. Among these methods, neighborhood-based methods are the mainstream methods. However, these methods ignore some meta-information about the items, specifically, the diversity of item information (e.g., texts) and feature interaction between neighboring nodes. In this paper, we propose a Bilinear Knowledge-aware Graph Neural Network Fusing Text Information (BKGNN-TI), which can model both knowledge graph information and text information. In particular, the information in knowledge graph contains not only the existing high-order connectivity but also feature interactions between neighboring nodes at the same level in KG. First, we construct the information propagation layer using the bilinear collector and linear collector. Feature interactions between neighboring nodes and the high-order connectivity are collected in the information propagation layer to generate the item knowledge representations. The bilinear collector emphasizes the importance of second-order feature interaction between neighboring nodes in the KG. Then, texts are also introduced when computing the item representations, which can help further infer user interests. We choose objective program titles and introductions as text information to avoid the influence of subjective factors. BKGNN-TI designs an ALBERT-based sequence encoder to encode texts by the structure of ALBERT+Bi-LSTM+Attention, thus enriching the feature representations of the items. In the experiments, we utilize two language datasets, i.e., the English public dataset Movielens-20M and the Chinese dataset IPTV constructed by ourselves. The results demonstrate that our BKGNN-TI outperforms baselines, indicating that our BKGNN-TI is a generalization for both Chinese and English datasets.

Existing knowledge graph-based recommendation algorithms either use Knowledge Graphs (KGs) as auxiliary information or use KG prediction tasks as regular terms to constrain recommendation with multi-task learning. However, the first method, which introduces multi-hop neighbors to enhance item representations, also weakens the relationship information within individual triples to some extent. The second method ignores neighboring information and thus fails to capture the long-range connectivity between items, which leads to a lack of utilization of the structural information in the KG. In response to the limitations of existing recommendation algorithms that do not fully leverage the relational and structural information within KGs, we propose a novel method named Knowledge-Enhanced Multi-Task Parallelized Recommendation Algorithm Incorporating Attention-Embedded Propagation (KMPR-AEP). It employs a parallel approach to simultaneously incorporate KG as auxiliary information and a regular term. We take into account the multi-hop neighbor information of users and items as well as enhance the relations among individual triples, which considers both the structural and relational information of KG. Extensive experiments conducted on three real-world datasets for CTR prediction and Top-K recommendation scenarios demonstrate the superiority of our proposed method over the state-of-the-art. On average, our KMPR-AEP shows improvements of 2.44% in AUC, 3.49% in ACC, and 2.64% in F1.

Even dispersion is important for live sound reinforcement systems; however, it needs to be carefully designed when using a linear loudspeaker array. This is because the audience area is often large, while the loudspeakers are placed centrally in this case for convenience, and thus both the level and the frequency balance may not remain reasonably constant for all audiences. To solve this problem, the adaptive genetic algorithm is firstly introduced in the parameters optimization. Secondly, taking the radiation characteristics at different frequencies into account, a linear-phase non-uniform filter bank is proposed to decompose the broad frequency band into several sub-bands. The audio is re-synthesized with the optimized parameters in each frequency band for a linear loudspeaker array. To show the validity of the proposed method, the simulations and the experiments are conducted to demonstrate that the sound pressure level in the audience area is distributed within $\pm 1.33$ dB, ranging from 200 Hz to 4000 Hz.

For the lack of adequate paired noisy-clean speech corpus in many real scenarios, non-parallel training is a promising task for DNN-based speech enhancement methods. However, because of the severe mismatch between input and target speeches, many previous studies only focus on the magnitude spectrum estimation and remain the phase unaltered, resulting in the degraded speech quality under low signal-to-noise ratio conditions. To tackle this problem, we decouple the difficult target w.r.t. original spectrum optimization into spectral magnitude and phase, and a novel Cycle-in-Cycle generative adversarial network (dubbed CinCGAN) is proposed to jointly estimate the spectral magnitude and phase information stage by stage under unpaired data. In the first stage, we pretrain a magnitude CycleGAN to coarsely estimate the spectral magnitude of clean speech. In the second stage, we incorporate the pretrained CycleGAN with a complex-valued CycleGAN as a cycle-in-cycle structure to simultaneously recover phase information and refine the overall spectrum. Experimental results demonstrate that the proposed approach significantly outperforms previous baselines under non-parallel training. The evaluation on training the models with standard paired data also shows that CinCGAN achieves remarkable performance especially in reducing background noise and speech distortion.

Non-parallel training is a difficult but essential task for DNN-based speech enhancement methods, for the lack of adequate noisy and paired clean speech corpus in many real scenarios. In this paper, we propose a novel adaptive attention-in-attention CycleGAN (AIA-CycleGAN) for non-parallel speech enhancement. In previous CycleGAN-based non-parallel speech enhancement methods, the limited mapping ability of the generator may cause performance degradation and insufficient feature learning. To alleviate this degradation, we propose an integration of adaptive time-frequency attention (ATFA) and adaptive hierarchical attention (AHA) to form an attention-in-attention (AIA) module for more flexible feature learning during the mapping procedure. More specifically, ATFA can capture the long-range temporal-spectral contextual information for more effective feature representations, while AHA can flexibly aggregate different AFTA's intermediate output feature maps by adaptive attention weights depending on the global context. Numerous experimental results demonstrate that the proposed approach achieves consistently more superior performance over previous GAN-based and CycleGAN-based methods in non-parallel training. Moreover, experiments in parallel training verify that the proposed AIA-CycleGAN also outperforms most advanced GAN-based and Non-GAN based speech enhancement approaches, especially in maintaining speech integrity and reducing speech distortion.