Xuewei Zhang

Xuewei Zhang, Tiejun Lv, Yuan Ren et al.

Aiming to minimize service delay, we propose a new random caching scheme in device-to-device (D2D)-assisted heterogeneous network. To support diversified viewing qualities of multimedia video services, each video file is encoded into a base layer (BL) and multiple enhancement layers (ELs) by scalable video coding (SVC). A super layer, including the BL and several ELs, is transmitted to every user. We define and quantify the service delay of multi-quality videos by deriving successful transmission probabilities when a user is served by a D2D helper, a small-cell base station (SBS) and a macro-cell base station (MBS). We formulate a delay minimization problem subject to the limited cache sizes of D2D helpers and SBSs. The structure of the optimal solutions to the problem is revealed, and then an improved standard gradient projection method is designed to effectively obtain the solutions. Both theoretical analysis and Monte-Carlo simulations validate the successful transmission probabilities. Compared with three benchmark caching policies, the proposed SVC-based random caching scheme is superior in terms of reducing the service delay.

Xuewei Zhang, Tiejun Lv, Yuan Ren et al.

We develop the optimal economical caching schemes in cache-enabled heterogeneous networks, while delivering multimedia video services with personalized viewing qualities to mobile users. By applying scalable video coding (SVC), each video file to be requested is divided into one base layer (BL) and several enhancement layers (ELs). In order to assign different transmission tasks, the serving small-cell base stations (SBSs) are grouped into K clusters. The SBSs are able to cache and cooperatively transmit BL and EL contents to the user. We analytically derive the expressions for successful transmission probability and ergodic service rate, and then the closed form of EConomical Efficiency (ECE) is obtained. In order to enhance the ECE performance, we formulate the ECE optimization problems for two cases. In the first case, with equal cache size equipped at each SBS, the layer caching indicator is determined. Since this problem is NP-hard, after the l0-norm approximation, the discrete optimization variables are relaxed to be continuous, and this relaxed problem is convex. Next, based on the optimal solution derived from the relaxed problem, we devise a greedystrategy based heuristic algorithm to achieve the near-optimal layer caching indicators. In the second case, the cache size for each SBS, the layer size and the layer caching indicator are jointly optimized. This problem is a mixed integer programming problem, which is more challenging. To effectively solve this problem, the original ECE maximization problem is divided into two subproblems. These two subproblems are iteratively solved until the original optimization problem is convergent. Numerical results verify the correctness of theoretical derivations. Additionally, compared to the most popular layer placement strategy, the performance superiority of the proposed SVC-based caching schemes is testified.

Chao Li, Xiaokong Ma, Bing Jiang et al.

We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including speaker identification, verification, and clustering. We experiment with ResCNN and GRU architectures to extract the acoustic features, then mean pool to produce utterance-level speaker embeddings, and train using triplet loss based on cosine similarity. Experiments on three distinct datasets suggest that Deep Speaker outperforms a DNN-based i-vector baseline. For example, Deep Speaker reduces the verification equal error rate by 50% (relatively) and improves the identification accuracy by 60% (relatively) on a text-independent dataset. We also present results that suggest adapting from a model trained with Mandarin can improve accuracy for English speaker recognition.

Dong Wang, Xuewei Zhang

Speech data is crucially important for speech recognition research. There are quite some speech databases that can be purchased at prices that are reasonable for most research institutes. However, for young people who just start research activities or those who just gain initial interest in this direction, the cost for data is still an annoying barrier. We support the `free data' movement in speech recognition: research institutes (particularly supported by public funds) publish their data freely so that new researchers can obtain sufficient data to kick of their career. In this paper, we follow this trend and release a free Chinese speech database THCHS-30 that can be used to build a full- edged Chinese speech recognition system. We report the baseline system established with this database, including the performance under highly noisy conditions.