Weibin Zhang

Jiatong Bai, Feng Shu, Qinghe Zheng et al.

Due to its excellent performance in rate and resolution, fully-digital (FD) massive multiple-input multiple-output (MIMO) antenna arrays has been widely applied in data transmission and direction of arrival (DOA) measurements, etc. But it confronts with two main challenges: high computational complexity and circuit cost. The two problems may be addressed well by hybrid analog-digital (HAD) structure. But there exists the problem of phase ambiguity for HAD, which leads to its low-efficiency or high-latency. Does exist there such a MIMO structure of owning low-cost, low-complexity and high time efficiency at the same time. To satisfy the three properties, a novel heterogeneous hybrid MIMO receiver structure of integrating FD and heterogeneous HAD ($\rm{H}^2$AD-FD) is proposed and corresponding multi-modal (MD)-learning framework is developed. The framework includes three major stages: 1) generate the candidate sets via root multiple signal classification (Root-MUSIC) or deep learning (DL); 2) infer the class of true solutions from candidate sets using machine learning (ML) methods; 3) fuse the two-part true solutions to achieve a better DOA estimation. The above process form two methods named MD-Root-MUSIC and MDDL. To improve DOA estimation accuracy and reduce the clustering complexity, a co-learning-aided MD framework is proposed to form two enhanced methods named CoMDDL and CoMD-RootMUSIC. Moreover, the Cramer-Rao lower bound (CRLB) for the proposed $\rm{H}^2$AD-FD structure is also derived. Experimental results demonstrate that our proposed four methods could approach the CRLB for signal-to-noise ratio (SNR) > 0 dB and the proposed CoMDDL and MDDL perform better than CoMD-RootMUSIC and MD-RootMUSIC, particularly in the extremely low SNR region.

Rongjin Li, Weibin Zhang, Dongpeng Chen

State-of-the-art speaker recognition systems are trained with a large amount of human-labeled training data set. Such a training set is usually composed of various data sources to enhance the modeling capability of models. However, in practical deployment, unseen condition is almost inevitable. Domain mismatch is a common problem in real-life applications due to the statistical difference between the training and testing data sets. To alleviate the degradation caused by domain mismatch, we propose a new feature-based unsupervised domain adaptation algorithm. The algorithm we propose is a further optimization based on the well-known CORrelation ALignment (CORAL), so we call it CORAL++. On the NIST 2019 Speaker Recognition Evaluation (SRE19), we use SRE18 CTS set as the development set to verify the effectiveness of CORAL++. With the typical x-vector/PLDA setup, the CORAL++ outperforms the CORAL by 9.40% relatively on EER.

Yufei Liu, Rao Ma, Haihua Xu et al.

An end-to-end (E2E) ASR model implicitly learns a prior Internal Language Model (ILM) from the training transcripts. To fuse an external LM using Bayes posterior theory, the log likelihood produced by the ILM has to be accurately estimated and subtracted. In this paper we propose two novel approaches to estimate the ILM based on Listen-Attend-Spell (LAS) framework. The first method is to replace the context vector of the LAS decoder at every time step with a vector that is learned with training transcripts. Furthermore, we propose another method that uses a lightweight feed-forward network to directly map query vector to context vector in a dynamic sense. Since the context vectors are learned by minimizing the perplexities on training transcripts, and their estimation is independent of encoder output, hence the ILMs are accurately learned for both methods. Experiments show that the ILMs achieve the lowest perplexity, indicating the efficacy of the proposed methods. In addition, they also significantly outperform the shallow fusion method, as well as two previously proposed ILM Estimation (ILME) approaches on several datasets.

Baiji Liu, Songjun Cao, Sining Sun et al.

The attention mechanism of the Listen, Attend and Spell (LAS) model requires the whole input sequence to calculate the attention context and thus is not suitable for online speech recognition. To deal with this problem, we propose multi-head monotonic chunk-wise attention (MTH-MoChA), an improved version of MoChA. MTH-MoChA splits the input sequence into small chunks and computes multi-head attentions over the chunks. We also explore useful training strategies such as LSTM pooling, minimum world error rate training and SpecAugment to further improve the performance of MTH-MoChA. Experiments on AISHELL-1 data show that the proposed model, along with the training strategies, improve the character error rate (CER) of MoChA from 8.96% to 7.68% on test set. On another 18000 hours in-car speech data set, MTH-MoChA obtains 7.28% CER, which is significantly better than a state-of-the-art hybrid system.

Jun Li, Zhichao Xing, Weibin Zhang et al.

Vehicle tracking has become one of the key applications of wireless sensor networks (WSNs) in the fields of rescue, surveillance, traffic monitoring, etc. However, the increased tracking accuracy requires more energy consumption. In this letter, a decentralized vehicle tracking strategy is conceived for improving both tracking accuracy and energy saving, which is based on adjusting the intersection area between the fixed sensing area and the dynamic activation area. Then, two deep reinforcement learning (DRL) aided solutions are proposed relying on the dynamic selection of the activation area radius. Finally, simulation results show the superiority of our DRL aided design.