arXiv subjects

Chen Zhang

Publications and source records attributed to Chen Zhang.

At least 559 records · Page 31Linked to original sources

arXiv2020

DenoiSpeech: Denoising Text to Speech with Frame-Level Noise Modeling

While neural-based text to speech (TTS) models can synthesize natural and intelligible voice, they usually require high-quality speech data, which is costly to collect. In many scenarios, only noisy speech of a target speaker is available, which presents challenges for TTS model training for this speaker. Previous works usually address the challenge using two methods: 1) training the TTS model using the speech denoised with an enhancement model; 2) taking a single noise embedding as input when training with noisy speech. However, they usually cannot handle speech with real-world complicated noise such as those with high variations along time. In this paper, we develop DenoiSpeech, a TTS system that can synthesize clean speech for a speaker with noisy speech data. In DenoiSpeech, we handle real-world noisy speech by modeling the fine-grained frame-level noise with a noise condition module, which is jointly trained with the TTS model. Experimental results on real-world data show that DenoiSpeech outperforms the previous two methods by 0.31 and 0.66 MOS respectively.

eess.AS↗

arXiv2020

UWSpeech: Speech to Speech Translation for Unwritten Languages

Existing speech to speech translation systems heavily rely on the text of target language: they usually translate source language either to target text and then synthesize target speech from text, or directly to target speech with target text for auxiliary training. However, those methods cannot be applied to unwritten target languages, which have no written text or phoneme available. In this paper, we develop a translation system for unwritten languages, named as UWSpeech, which converts target unwritten speech into discrete tokens with a converter, and then translates source-language speech into target discrete tokens with a translator, and finally synthesizes target speech from target discrete tokens with an inverter. We propose a method called XL-VAE, which enhances vector quantized variational autoencoder (VQ-VAE) with cross-lingual (XL) speech recognition, to train the converter and inverter of UWSpeech jointly. Experiments on Fisher Spanish-English conversation translation dataset show that UWSpeech outperforms direct translation and VQ-VAE baseline by about 16 and 10 BLEU points respectively, which demonstrate the advantages and potentials of UWSpeech.

eess.AS↗

arXiv2020

Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction

Image reconstruction methods based on deep neural networks have shown outstanding performance, equalling or exceeding the state-of-the-art results of conventional approaches, but often do not provide uncertainty information about the reconstruction. In this work we propose a scalable and efficient framework to simultaneously quantify aleatoric and epistemic uncertainties in learned iterative image reconstruction. We build on a Bayesian deep gradient descent method for quantifying epistemic uncertainty, and incorporate the heteroscedastic variance of the noise to account for the aleatoric uncertainty. We show that our method exhibits competitive performance against conventional benchmarks for computed tomography with both sparse view and limited angle data. The estimated uncertainty captures the variability in the reconstructions, caused by the restricted measurement model, and by missing information, due to the limited angle geometry.

cs.CV↗

arXiv2020

Unruh-DeWitt Detector Differentiation of Black Holes and Exotic Compact Objects

We study the response of a static Unruh-DeWitt detector outside an exotic compact object (ECO) with a general reflective boundary condition in 3+1 dimensions. The horizonless ECO, whose boundary is extremely close to the would-be event horizon, acts as a black hole mimicker. We find that the response rate is notably distinct from the black hole case, even when the ECO boundary is perfectly absorbing. For a (partially) reflective ECO boundary, we find resonance structures in the response rate that depend on the different locations of the ECO boundary and those of the detector. We provide a detailed analysis in connection with the ECO's vacuum mode structure and transfer function.

gr-qc↗

arXiv2020

Towards Persona-Based Empathetic Conversational Models

Empathetic conversational models have been shown to improve user satisfaction and task outcomes in numerous domains. In Psychology, persona has been shown to be highly correlated to personality, which in turn influences empathy. In addition, our empirical analysis also suggests that persona plays an important role in empathetic conversations. To this end, we propose a new task towards persona-based empathetic conversations and present the first empirical study on the impact of persona on empathetic responding. Specifically, we first present a novel large-scale multi-domain dataset for persona-based empathetic conversations. We then propose CoBERT, an efficient BERT-based response selection model that obtains the state-of-the-art performance on our dataset. Finally, we conduct extensive experiments to investigate the impact of persona on empathetic responding. Notably, our results show that persona improves empathetic responding more when CoBERT is trained on empathetic conversations than non-empathetic ones, establishing an empirical link between persona and empathy in human conversations.

cs.CL↗

arXiv2020

A Multi-task Learning Framework for Opinion Triplet Extraction

The state-of-the-art Aspect-based Sentiment Analysis (ABSA) approaches are mainly based on either detecting aspect terms and their corresponding sentiment polarities, or co-extracting aspect and opinion terms. However, the extraction of aspect-sentiment pairs lacks opinion terms as a reference, while co-extraction of aspect and opinion terms would not lead to meaningful pairs without determining their sentiment dependencies. To address the issue, we present a novel view of ABSA as an opinion triplet extraction task, and propose a multi-task learning framework to jointly extract aspect terms and opinion terms, and simultaneously parses sentiment dependencies between them with a biaffine scorer. At inference phase, the extraction of triplets is facilitated by a triplet decoding method based on the above outputs. We evaluate the proposed framework on four SemEval benchmarks for ASBA. The results demonstrate that our approach significantly outperforms a range of strong baselines and state-of-the-art approaches.

cs.CL↗

arXiv2020

LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression

BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks. However, a major blocking issue of applying BERT to online services is that it is memory-intensive and leads to unsatisfactory latency of user requests, raising the necessity of model compression. Existing solutions leverage the knowledge distillation framework to learn a smaller model that imitates the behaviors of BERT. However, the training procedure of knowledge distillation is expensive itself as it requires sufficient training data to imitate the teacher model. In this paper, we address this issue by proposing a hybrid solution named LadaBERT (Lightweight adaptation of BERT through hybrid model compression), which combines the advantages of different model compression methods, including weight pruning, matrix factorization and knowledge distillation. LadaBERT achieves state-of-the-art accuracy on various public datasets while the training overheads can be reduced by an order of magnitude.

cs.CL↗

arXiv2020

Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent

Recent advances in reconstruction methods for inverse problems leverage powerful data-driven models, e.g., deep neural networks. These techniques have demonstrated state-of-the-art performances for several imaging tasks, but they often do not provide uncertainty on the obtained reconstruction. In this work, we develop a scalable, data-driven, knowledge-aided computational framework to quantify the model uncertainty via Bayesian neural networks. The approach builds on, and extends deep gradient descent, a recently developed greedy iterative training scheme, and recasts it within a probabilistic framework. Scalability is achieved by being hybrid in the architecture: only the last layer of each block is Bayesian, while the others remain deterministic, and by being greedy in training. The framework is showcased on one representative medical imaging modality, viz. computed tomography with either sparse view or limited view data, and exhibits competitive performance with respect to state-of-the-art benchmarks, e.g., total variation, deep gradient descent and learned primal-dual.

cs.CV↗

arXiv2020

Partially Observable Online Change Detection via Smooth-Sparse Decomposition

We consider online change detection of high dimensional data streams with sparse changes, where only a subset of data streams can be observed at each sensing time point due to limited sensing capacities. On the one hand, the detection scheme should be able to deal with partially observable data and meanwhile have efficient detection power for sparse changes. On the other, the scheme should be able to adaptively and actively select the most important variables to observe to maximize the detection power. To address these two points, in this paper, we propose a novel detection scheme called CDSSD. In particular, it describes the structure of high dimensional data with sparse changes by smooth-sparse decomposition, whose parameters can be learned via spike-slab variational Bayesian inference. Then the posterior Bayes factor, which incorporates the learned parameters and sparse change information, is formulated as a detection statistic. Finally, by formulating the statistic as the reward of a combinatorial multi-armed bandit problem, an adaptive sampling strategy based on Thompson sampling is proposed. The efficacy and applicability of our method in practice are demonstrated with numerical studies and a real case study.

stat.ML↗

arXiv2020

Crowding Prediction of In-Situ Metro Passengers Using Smart Card Data

The metro system is playing an increasingly important role in the urban public transit network, transferring a massive human flow across space everyday in the city. In recent years, extensive research studies have been conducted to improve the service quality of metro systems. Among them, crowd management has been a critical issue for both public transport agencies and train operators. In this paper, by utilizing accumulated smart card data, we propose a statistical model to predict in-situ passenger density, i.e., number of on-board passengers between any two neighbouring stations, inside a closed metro system. The proposed model performs two main tasks: i) forecasting time-dependent Origin-Destination (OD) matrix by applying mature statistical models; and ii) estimating the travel time cost required by different parts of the metro network via truncated normal mixture distributions with Expectation-Maximization (EM) algorithm. Based on the prediction results, we are able to provide accurate prediction of in-situ passenger density for a future time point. A case study using real smart card data in Singapore Mass Rapid Transit (MRT) system demonstrate the efficacy and efficiency of our proposed method.

cs.LG↗

arXiv2020

Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation

Non-autoregressive translation (NAT) achieves faster inference speed but at the cost of worse accuracy compared with autoregressive translation (AT). Since AT and NAT can share model structure and AT is an easier task than NAT due to the explicit dependency on previous target-side tokens, a natural idea is to gradually shift the model training from the easier AT task to the harder NAT task. To smooth the shift from AT training to NAT training, in this paper, we introduce semi-autoregressive translation (SAT) as intermediate tasks. SAT contains a hyperparameter k, and each k value defines a SAT task with different degrees of parallelism. Specially, SAT covers AT and NAT as its special cases: it reduces to AT when k = 1 and to NAT when k = N (N is the length of target sentence). We design curriculum schedules to gradually shift k from 1 to N, with different pacing functions and number of tasks trained at the same time. We called our method as task-level curriculum learning for NAT (TCL-NAT). Experiments on IWSLT14 De-En, IWSLT16 En-De, WMT14 En-De and De-En datasets show that TCL-NAT achieves significant accuracy improvements over previous NAT baselines and reduces the performance gap between NAT and AT models to 1-2 BLEU points, demonstrating the effectiveness of our proposed method.

cs.CL↗

arXiv2020

Quantum nucleation of up-down quark matter and astrophysical implications

Quark matter with only $u$ and $d$ quarks ($ud$QM) might be the ground state of baryonic matter at large baryon number $A>A_{\rm min}$. With $A_{\rm min}\gtrsim 300$, this has no direct conflict with the stability of ordinary nuclei. An intriguing test of this scenario is to look for quantum nucleation of $ud$QM inside neutron stars due to their large baryon densities. In this paper, we study the transition rate of cold neutron stars to $ud$ quark stars ($ud$QSs) and the astrophysical implications, considering the relevant theoretical uncertainties and observational constraints. It turns out that a large portion of parameter space predicts an instantaneous transition, and so the observed neutron stars are mostly $ud$QSs. We find this possibility still viable under the recent gravitational wave and pulsar observations, although there are debates on its compatibility with some observations that involve complicated structure of quark matter. The tension could be partially relieved in the two-families scenario, where the high-mass stars ($M\gtrsim2 M_{\odot}$) are all $ud$QSs and the low-mass ones ($M\sim1.4\, M_{\odot}$) are mostly hadronic stars. In this case, the slow transition of the low-mass hadronic stars points to a very specific class of hadronic models with moderately stiff EOSs, and $ud$QM properties are also strongly constrained.

hep-ph↗

arXiv2020

Charging the Walking U(N)$\times$U(N) Higgs Theory as a Complex CFT

We apply a semi-classical method to compute the conformal field theory (CFT) data for the U(N)xU(N) non-abelian Higgs theory in four minus epsilon dimensions at its complex fixed point. The theory features more than one coupling and walking dynamics. Given our charge configuration, we identify a family of corresponding operators and compute their scaling dimensions which remarkably agree with available results from conventional perturbation theory validating the use of the state-operator correspondence for a complex CFT.

hep-th↗

arXiv2020

A Survey on Dynamic Network Embedding

Real-world networks are composed of diverse interacting and evolving entities, while most of existing researches simply characterize them as particular static networks, without consideration of the evolution trend in dynamic networks. Recently, significant progresses in tracking the properties of dynamic networks have been made, which exploit changes of entities and links in the network to devise network embedding techniques. Compared to widely proposed static network embedding methods, dynamic network embedding endeavors to encode nodes as low-dimensional dense representations that effectively preserve the network structures and the temporal dynamics, which is beneficial to multifarious downstream machine learning tasks. In this paper, we conduct a systematical survey on dynamic network embedding. In specific, basic concepts of dynamic network embedding are described, notably, we propose a novel taxonomy of existing dynamic network embedding techniques for the first time, including matrix factorization based, Skip-Gram based, autoencoder based, neural networks based and other embedding methods. Additionally, we carefully summarize the commonly used datasets and a wide variety of subsequent tasks that dynamic network embedding can benefit. Afterwards and primarily, we suggest several challenges that the existing algorithms faced and outline possible directions to facilitate the future research, such as dynamic embedding models, large-scale dynamic networks, heterogeneous dynamic networks, dynamic attributed networks, task-oriented dynamic network embedding and more embedding spaces.

cs.SI↗

arXiv2020

The Techni-Pati-Salam Composite Higgs

Composite Higgs models can be extended to the Planck scale by means of the partially unified partial compositeness (PUPC) framework. We present in detail the Techni-Pati-Salam model, based on a renormalizable gauge theory $SU(8)_{PS}\times SU(2)_L\times SU(2)_R$. We demonstrate that masses and mixings for all generations of standard model fermions can be obtained via partial compositeness at low energy, with four-fermion operators mediated by either heavy gauge bosons or scalars. The strong dynamics is predicted to be that of a confining $Sp(4)_{\rm HC}$ gauge group, with hyper-fermions in the fundamental and two-index anti-symmetric representations, with fixed multiplicities. This motivates for Lattice studies of the Infra-Red near-conformal walking phase, with results that may validate or rule out the model. This is the first complete and realistic attempt at providing an Ultra-Violet completion for composite Higgs models with top partial compositeness. In the baryon-number conserving vacuum, the theory also predicts a Dark Matter candidate, with mass in the few TeV range, protected by semi-integer baryon number.

hep-ph↗

arXiv2020

Long-Short Term Spatiotemporal Tensor Prediction for Passenger Flow Profile

Spatiotemporal data is very common in many applications, such as manufacturing systems and transportation systems. It is typically difficult to be accurately predicted given intrinsic complex spatial and temporal correlations. Most of the existing methods based on various statistical models and regularization terms, fail to preserve innate features in data alongside their complex correlations. In this paper, we focus on a tensor-based prediction and propose several practical techniques to improve prediction. For long-term prediction specifically, we propose the "Tensor Decomposition + 2-Dimensional Auto-Regressive Moving Average (2D-ARMA)" model, and an effective way to update prediction real-time; For short-term prediction, we propose to conduct tensor completion based on tensor clustering to avoid oversimplifying and ensure accuracy. A case study based on the metro passenger flow data is conducted to demonstrate the improved performance.

cs.LG↗

arXiv2020

Microwave-free vector magnetometry with nitrogen-vacancy centers along a single axis in diamond

Sensing vector magnetic fields is critical to many applications in fundamental physics, bioimaging, and material science. Magnetic-field sensors exploiting nitrogen-vacancy (NV) centers are particularly compelling as they offer high sensitivity and spatial resolution even at nanoscale. Achieving vector magnetometry has, however, often required applying microwaves sequentially or simultaneously, limiting the sensors' applications under cryogenic temperature. Here we propose and demonstrate a microwave-free vector magnetometer that simultaneously measures all Cartesian components of a magnetic field using NV ensembles in diamond. In particular, the present magnetometer leverages the level anticrossing in the triplet ground state at 102.4 mT, allowing the measurement of both longitudinal and transverse fields with a wide bandwidth from zero to megahertz range. Full vector sensing capability is proffered by modulating fields along the preferential NV axis and in the transverse plane and subsequent demodulation of the signal. This sensor exhibits a root mean square noise floor of about 300 pT/Hz^(1/2) in all directions. The present technique is broadly applicable to both ensemble sensors and potentially also single-NV sensors, extending the vector capability to nanoscale measurement under ambient temperatures.

physics.app-ph↗

arXiv2020

A Driver Fatigue Recognition Algorithm Based on Spatio-Temporal Feature Sequence

Researches show that fatigue driving is one of the important causes of road traffic accidents, so it is of great significance to study the driver fatigue recognition algorithm to improve road traffic safety. In recent years, with the development of deep learning, the field of pattern recognition has made great development. This paper designs a real-time fatigue state recognition algorithm based on spatio-temporal feature sequence, which can be mainly applied to the scene of fatigue driving recognition. The algorithm is divided into three task networks: face detection network, facial landmark detection and head pose estimation network, fatigue recognition network. Experiments show that the algorithm has the advantages of small volume, high speed and high accuracy.

cs.CV↗