arXiv subjects

Zhiyong Wu

Publications and source records attributed to Zhiyong Wu.

223 records · Page 13Linked to original sources

arXiv2020

Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks

Self-attention network (SAN) can benefit significantly from the bi-directional representation learning through unsupervised pretraining paradigms such as BERT and XLNet. In this paper, we present an XLNet-like pretraining scheme "Speech-XLNet" for unsupervised acoustic model pretraining to learn speech representations with SAN. The pretrained SAN is finetuned under the hybrid SAN/HMM framework. We conjecture that by shuffling the speech frame orders, the permutation in Speech-XLNet serves as a strong regularizer to encourage the SAN to make inferences by focusing on global structures through its attention weights. In addition, Speech-XLNet also allows the model to explore the bi-directional contexts for effective speech representation learning. Experiments on TIMIT and WSJ demonstrate that Speech-XLNet greatly improves the SAN/HMM performance in terms of both convergence speed and recognition accuracy compared to the one trained from randomly initialized weights. Our best systems achieve a relative improvement of 11.9% and 8.3% on the TIMIT and WSJ tasks respectively. In particular, the best system achieves a phone error rate (PER) of 13.3% on the TIMIT test set, which to our best knowledge, is the lowest PER obtained from a single system.

cs.CL↗

arXiv2017

Strong Exciton-Photon Coupling and lasing behavior in All-Inorganic CsPbBr3 Micro/nanowire Fabry-Perot cavity

Macroscopic spontaneous coherence of exciton-polariton in semiconductor cavity is one important research field in condensed matter physics. All-inorganic micro/nanowire Fabry-Pérot cavity with excellent optical performance makes it possible to realize strong coupling and lasing of exciton-photon at room temperature. In this work, we demonstrated strong coupling of exciton-photon and polariton lasing in CsPbBr3 micro/nanowires synthesized by CVD method. By exploring spatial resolved PL spectra of CsPbBr3 cavity, we observed mode volume dependent coupling strength , as well as significant increase in group index. Moreover, low threshold polariton lasing was achieved at room temperature within strong coupling regime; the polariton characteristic is confirmed by comparing lasing spectra with waveguided output spectra and the dramatically reduced lasing threshold. Our present results provide new avenues to achieve high coupling strengths potentially enabling application of exciting phenomena such as Bose-Einstein condensation of polaritons, efficient light-emitting diodes and lasers.

cond-mat.mes-hall↗

arXiv2017

Exciton-Polaritons in Hybrid Inorganic-organic Perovskite Fabry-Pérot Microcavity

Exciton-polaritons in semiconductor microcavities generate fascinating effects such as long-range spatial coherence and Bose-Einstein Condensation (BEC), which are attractive for their potential use in low threshold lasers, vortices and slowing light, etc. However, currently most of exciton-polariton effects either occur at cryogenic temperature or rely on expensive cavity fabrication procedures. Further exploring new semiconductor microcavities with stronger exciton photon interaction strength is extensively needed. Herein, we demonstrate room temperature photon exciton strong coupling in hybrid inorganic-organic CH3NH3PbBr3 Fabry-Pérot microcavities for the first time. The vacuum Rabi splitting energy is up to ~390 meV, which is ascribed to large oscillator strength and photon confinement in reduced dimension of optical microcavities. With increasing pumping energy, exciton-photon coupling strength is weakened due to carrier screening effect, leading to occurrence of photonic lasing instead of polartion lasing. The demonstrated strong coupling between photons and excitons in perovskite microcavities would be helpful for development of high performance polariton-based incoherent and coherent light sources, nonlinear optics, and slow light applications.

cond-mat.mes-hall↗

arXiv2017

NEXT: A Neural Network Framework for Next POI Recommendation

The task of next POI recommendation has been studied extensively in recent years. However, developing an unified recommendation framework to incorporate multiple factors associated with both POIs and users remains challenging, because of the heterogeneity nature of these information. Further, effective mechanisms to handle cold-start and endow the system with interpretability are also difficult topics. Inspired by the recent success of neural networks in many areas, in this paper, we present a simple but effective neural network framework for next POI recommendation, named NEXT. NEXT is an unified framework to learn the hidden intent regarding user's next move, by incorporating different factors in an unified manner. Specifically, in NEXT, we incorporate meta-data information and two kinds of temporal contexts (i.e., time interval and visit time). To leverage sequential relations and geographical influence, we propose to adopt DeepWalk, a network representation learning technique, to encode such knowledge. We evaluate the effectiveness of NEXT against state-of-the-art alternatives and neural networks based solutions. Experimental results over three publicly available datasets demonstrate that NEXT significantly outperforms baselines in real-time next POI recommendation. Further experiments demonstrate the superiority of NEXT in handling cold-start. More importantly, we show that NEXT provides meaningful explanation of the dimensions in hidden intent space.

cs.IR↗

arXiv2017

Measuring and Maximizing Influence via Random Walk in Social Activity Networks

With the popularity of OSNs, finding a set of most influential users (or nodes) so as to trigger the largest influence cascade is of significance. For example, companies may take advantage of the "word-of-mouth" effect to trigger a large cascade of purchases by offering free samples/discounts to those most influential users. This task is usually modeled as an influence maximization problem, and it has been widely studied in the past decade. However, considering that users in OSNs may participate in various kinds of online activities, e.g., giving ratings to products, joining discussion groups, etc., influence diffusion through online activities becomes even more significant. In this paper, we study the impact of online activities by formulating the influence maximization problem for social-activity networks (SANs) containing both users and online activities. To address the computation challenge, we define an influence centrality via random walks to measure influence, then use the Monte Carlo framework to efficiently estimate the centrality in SANs. Furthermore, we develop a greedy-based algorithm with two novel optimization techniques to find the most influential users. By conducting extensive experiments with real-world datasets, we show our approach is more efficient than the state-of-the-art algorithm IMM[17] when we needs to handle large amount of online activities.

cs.SI↗

arXiv2016

Study on Feature Subspace of Archetypal Emotions for Speech Emotion Recognition

Feature subspace selection is an important part in speech emotion recognition. Most of the studies are devoted to finding a feature subspace for representing all emotions. However, some studies have indicated that the features associated with different emotions are not exactly the same. Hence, traditional methods may fail to distinguish some of the emotions with just one global feature subspace. In this work, we propose a new divide and conquer idea to solve the problem. First, the feature subspaces are constructed for all the combinations of every two different emotions (emotion-pair). Bi-classifiers are then trained on these feature subspaces respectively. The final emotion recognition result is derived by the voting and competition method. Experimental results demonstrate that the proposed method can get better results than the traditional multi-classification method.

cs.LG↗

arXiv2013

Feature Learning with Gaussian Restricted Boltzmann Machine for Robust Speech Recognition

In this paper, we first present a new variant of Gaussian restricted Boltzmann machine (GRBM) called multivariate Gaussian restricted Boltzmann machine (MGRBM), with its definition and learning algorithm. Then we propose using a learned GRBM or MGRBM to extract better features for robust speech recognition. Our experiments on Aurora2 show that both GRBM-extracted and MGRBM-extracted feature performs much better than Mel-frequency cepstral coefficient (MFCC) with either HMM-GMM or hybrid HMM-deep neural network (DNN) acoustic model, and MGRBM-extracted feature is slightly better.

cs.CL↗