arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 1,261 records · Page 70Linked to original sources

arXiv2021

WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis

This paper introduces WaveGrad 2, a non-autoregressive generative model for text-to-speech synthesis. WaveGrad 2 is trained to estimate the gradient of the log conditional density of the waveform given a phoneme sequence. The model takes an input phoneme sequence, and through an iterative refinement process, generates an audio waveform. This contrasts to the original WaveGrad vocoder which conditions on mel-spectrogram features, generated by a separate model. The iterative refinement process starts from Gaussian noise, and through a series of refinement steps (e.g., 50 steps), progressively recovers the audio sequence. WaveGrad 2 offers a natural way to trade-off between inference speed and sample quality, through adjusting the number of refinement steps. Experiments show that the model can generate high fidelity audio, approaching the performance of a state-of-the-art neural TTS system. We also report various ablation studies over different model configurations. Audio samples are available at https://wavegrad.github.io/v2.

eess.AS↗

arXiv2021

Variational Quantum Eigensolver with Reduced Circuit Complexity

The variational quantum eigensolver (VQE) is one of the most promising algorithms to find eigenvalues and eigenvectors of a given Hamiltonian on noisy intermediate-scale quantum (NISQ) devices. A particular application is to obtain ground or excited states of molecules. The practical realization is currently limited by the complexity of quantum circuits. Here we present a novel approach to reduce quantum circuit complexity in VQE for electronic structure calculations. Our algorithm, called ClusterVQE, splits the initial qubit space into subspaces (qubit clusters) which are further distributed on individual (shallower) quantum circuits. The clusters are obtained based on quantum mutual information reflecting maximal entanglement between qubits, whereas entanglement between different clusters is taken into account via a new "dressed" Hamiltonian. ClusterVQE therefore allows exact simulation of the problem by using fewer qubits and shallower circuit depth compared to standard VQE at the cost of additional classical resources. In addition, a new gradient measurement method without using an ancillary qubit is also developed in this work. Proof-of-principle demonstrations are presented for several molecular systems based on quantum simulators as well as an IBM quantum device with accompanying error mitigation. The efficiency of the new algorithm is comparable to or even improved over qubit-ADAPT-VQE and iterative Qubit Coupled Cluster (iQCC), state-of-the-art circuit-efficient VQE methods to obtain variational ground state energies of molecules on NISQ hardware. Above all, the new ClusterVQE algorithm simultaneously reduces the number of qubits and circuit depth, making it a potential leader for quantum chemistry simulations on NISQ devices.

quant-ph↗

arXiv2021

PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS

This paper introduces PnG BERT, a new encoder model for neural TTS. This model is augmented from the original BERT model, by taking both phoneme and grapheme representations of text as input, as well as the word-level alignment between them. It can be pre-trained on a large text corpus in a self-supervised manner, and fine-tuned in a TTS task. Experimental results show that a neural TTS model using a pre-trained PnG BERT as its encoder yields more natural prosody and more accurate pronunciation than a baseline model using only phoneme input with no pre-training. Subjective side-by-side preference evaluations show that raters have no statistically significant preference between the speech synthesized using a PnG BERT and ground truth recordings from professional speakers.

cs.CL↗

arXiv2021

FedNILM: Applying Federated Learning to NILM Applications at the Edge

Non-intrusive load monitoring (NILM) helps disaggregate the household's main electricity consumption to energy usages of individual appliances, thus greatly cutting down the cost in fine-grained household load monitoring. To address the arisen privacy concern in NILM applications, federated learning (FL) could be leveraged for NILM model training and sharing. When applying the FL paradigm in real-world NILM applications, however, we are faced with the challenges of edge resource restriction, edge model personalization and edge training data scarcity. In this paper we present FedNILM, a practical FL paradigm for NILM applications at the edge client. Specifically, FedNILM is designed to deliver privacy-preserving and personalized NILM services to large-scale edge clients, by leveraging i) secure data aggregation through federated learning, ii) efficient cloud model compression via filter pruning and multi-task learning, and iii) personalized edge model building with unsupervised transfer learning. Our experiments on real-world energy data show that, FedNILM is able to achieve personalized energy disaggregation with the state-of-the-art accuracy, while ensuring privacy preserving at the edge client.

cs.LG↗

arXiv2021

Rethinking Training from Scratch for Object Detection

The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization technique. In this paper, we explore to directly pre-training on target dataset for object detection. Under this situation, we discover that the widely adopted large resizing strategy e.g. resize image to (1333, 800) is important for fine-tuning but it's not necessary for pre-training. Specifically, we propose a new training pipeline for object detection that follows `pre-training and fine-tuning', utilizing low resolution images within target dataset to pre-training detector then load it to fine-tuning with high resolution images. With this strategy, we can use batch normalization(BN) with large bath size during pre-training, it's also memory efficient that we can apply it on machine with very limited GPU memory(11G). We call it direct detection pre-training, and also use direct pre-training for short. Experiment results show that direct pre-training accelerates the pre-training phase by more than 11x on COCO dataset while with even +1.8mAP compared to ImageNet pre-training. Besides, we found direct pre-training is also applicable to transformer based backbones e.g. Swin Transformer. Code will be available.

cs.CV↗

arXiv2021

More Behind Your Electricity Bill: a Dual-DNN Approach to Non-Intrusive Load Monitoring

Non-intrusive load monitoring (NILM) is a well-known single-channel blind source separation problem that aims to decompose the household energy consumption into itemised energy usage of individual appliances. In this way, considerable energy savings could be achieved by enhancing household's awareness of energy usage. Recent investigations have shown that deep neural networks (DNNs) based approaches are promising for the NILM task. Nevertheless, they normally ignore the inherent properties of appliance operations in the network design, potentially leading to implausible results. We are thus motivated to develop the dual Deep Neural Networks (dual-DNN), which aims to i) take advantage of DNNs' learning capability of latent features and ii) empower the DNN architecture with identification ability of universal properties. Specifically in the design of dual-DNN, we adopt one subnetwork to measure power ratings of different appliances' operation states, and the other subnetwork to identify the running states of target appliances. The final result is then obtained by multiplying these two network outputs and meanwhile considering the multi-state property of household appliances. To enforce the sparsity property in appliance's state operating, we employ median filtering and hard gating mechanisms to the subnetwork for state identification. Compared with the state-of-the-art NILM methods, our dual-DNN approach demonstrates a 21.67% performance improvement in average on two public benchmark datasets.

cs.LG↗

arXiv2021

Analysis of the differential cross section and photon beam asymmetry data for $γp \to η^\prime p$

The photoproduction reaction of $γp \to η^\prime p$ is investigated based on an effective Lagrangian approach in the tree-level approximation, with the purpose being to understand the reaction mechanisms and to extract the resonance contents and the associated resonance parameters in this reaction. Apart from the $t$-channel $ρ$ and $ω$ exchanges, $s$- and $u$-channel nucleon exchanges, and generalized contact term, the exchanges of a minimum number of nucleon resonances in the $s$ channel are taken into account in constructing the reaction amplitudes to describe the experimental data. It is found that a satisfactory description of the available data on both differential cross sections and photon beam asymmetries can be obtained by including in the $s$ channel the exchanges of the $N(1875)3/2^-$ and $N(2040)3/2^+$ resonances. The reaction mechanisms of $γp \to η^\prime p$ are discussed and a prediction for the target nucleon asymmetries is presented.

hep-ph↗

arXiv2021

Constraining nonstandard neutrino interactions at electron colliders

The presence of nonstandard neutrino interactions (NSI) has a large effect on the precision measurements at next generation neutrino oscillation experiments. Other type of experiments are needed to constrain the NSI parameter space. We study the constraints on NSI with electrons from current and future $e^+e^-$ collider experiments including Belle II, STCF and CEPC. We find that Belle II and STCF will provide competitive and complementary bounds on electron-type NSI parameters compared to the current global analysis, and strong improvements for the constraints on tau-type NSI. In addition, CEPC alone will impose stringent constraints on the parameter space of NSI with electrons. We find that the degeneracy between the left-handed (vector) and right-handed (axial-vector) NSI parameters can be lifted by combining the data from three different running modes, and the allowed ranges for $|ε_{ee}^{eL}|$ ($|ε_{ee}^{eV}|$) and $|ε_{ee}^{eR}|$ ($|ε_{ee}^{eA}|$) can be constrained to be smaller than 0.002 at CEPC even if both of them are present.

hep-ph↗

arXiv2021

Large-Signal Grid-Synchronization Stability Analysis of PLL-based VSCs Using Lyapunov's Direct Method

Grid-synchronization stability (GSS) is an emerging stability issue of grid-tied voltage source converters (VSCs), which can be provoked by severe grid voltage sags. Although a qualitative understanding of the mechanism behind the loss of synchronization has been acquired in recent studies, an analytical method for quantitative assessment of GSS of grid-tied VSCs is still missing. To bridge this gap, a dedicated Lyapunov function is analytically proposed, and its corresponding stability criterion for GSS analysis of grid-tied VSCs is rigorously constructed. Both theoretical analysis and simulation result demonstrate that the proposed method can provide a credible GSS evaluation compared to the previous EAC/EF-based method. Therefore, it can be applied for fast GSS evaluation of the grid-tied VSCs as is exemplified in this paper, as well as an analytical tool for some GSS-related issues, e.g., GSS-oriented parameter design and stabilization control.

eess.SY↗

arXiv2021

Origin Pilot: a Quantum Operating System for Effecient Usage of Quantum Resources

The operating system is designed to manage the hardware and software resources of a computer. With the development of quantum computing, the management of quantum resources and cooperation between quantum systems and other computing resources (e.g. CPU, GPU and FPGA etc.) become the key challenge for the application of quantum computing to solve real world problems. In this paper we propose a quantum operating system, Origin Pilot. Origin Pilot includes the module of quantum task scheduling, quantum resource management, quantum program compilation and qubits' automatic calibration. With these modules, Origin Pilot can manage the quantum computing resources and solve the multi-quantum processor scheduling problem. It can also allow the parallel execution of multiple quantum programs and calibrate the quantum resource effectively. Thus, the performance of resources is guaranteed and the resource utilization is improved. By comparing the results with and without Origin Pilot, we evaluate the impact on a quantum circuit's fidelity of qubits mapping algorithm. We also evaluate the effectiveness of automatic calibration and parallel execution of multi-quantum processors. Finally, Origin Pilot can be easily customized for hybrid computing resources.

quant-ph↗

arXiv2021

Attention-guided Chained Context Aggregation for Semantic Segmentation

The way features propagate in Fully Convolutional Networks is of momentous importance to capture multi-scale contexts for obtaining precise segmentation masks. This paper proposes a novel series-parallel hybrid paradigm called the Chained Context Aggregation Module (CAM) to diversify feature propagation. CAM gains features of various spatial scales through chain-connected ladder-style information flows and fuses them in a two-stage process, namely pre-fusion and re-fusion. The serial flow continuously increases receptive fields of output neurons and those in parallel encode different region-based contexts. Each information flow is a shallow encoder-decoder with appropriate down-sampling scales to sufficiently capture contextual information. We further adopt an attention model in CAM to guide feature re-fusion. Based on these developments, we construct the Chained Context Aggregation Network (CANet), which employs an asymmetric decoder to recover precise spatial details of prediction maps. We conduct extensive experiments on six challenging datasets, including Pascal VOC 2012, Pascal Context, Cityscapes, CamVid, SUN-RGBD and GATECH. Results evidence that CANet achieves state-of-the-art performance.

cs.CV↗

arXiv2021

A Multi-spectral Dataset for Evaluating Motion Estimation Systems

Visible images have been widely used for motion estimation. Thermal images, in contrast, are more challenging to be used in motion estimation since they typically have lower resolution, less texture, and more noise. In this paper, a novel dataset for evaluating the performance of multi-spectral motion estimation systems is presented. All the sequences are recorded from a handheld multi-spectral device. It consists of a standard visible-light camera, a long-wave infrared camera, an RGB-D camera, and an inertial measurement unit (IMU). The multi-spectral images, including both color and thermal images in full sensor resolution (640 x 480), are obtained from a standard and a long-wave infrared camera at 32Hz with hardware-synchronization. The depth images are captured by a Microsoft Kinect2 and can have benefits for learning cross-modalities stereo matching. For trajectory evaluation, accurate ground-truth camera poses obtained from a motion capture system are provided. In addition to the sequences with bright illumination, the dataset also contains dim, varying, and complex illumination scenes. The full dataset, including raw data and calibration data with detailed data format specifications, is publicly available.

cs.CV↗

arXiv2021

Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling

This paper presents Non-Attentive Tacotron based on the Tacotron 2 text-to-speech model, replacing the attention mechanism with an explicit duration predictor. This improves robustness significantly as measured by unaligned duration ratio and word deletion rate, two metrics introduced in this paper for large-scale robustness evaluation using a pre-trained speech recognition model. With the use of Gaussian upsampling, Non-Attentive Tacotron achieves a 5-scale mean opinion score for naturalness of 4.41, slightly outperforming Tacotron 2. The duration predictor enables both utterance-wide and per-phoneme control of duration at inference time. When accurate target durations are scarce or unavailable in the training data, we propose a method using a fine-grained variational auto-encoder to train the duration predictor in a semi-supervised or unsupervised manner, with results almost as good as supervised training.

cs.SD↗

arXiv2021

Learn to Predict Vertical Track Irregularity with Extremely Imbalanced Data

Railway systems require regular manual maintenance, a large part of which is dedicated to inspecting track deformation. Such deformation might severely impact trains' runtime security, whereas such inspections remain costly for both finance and human resources. Therefore, a more precise and efficient approach to detect railway track deformation is in urgent need. In this paper, we showcase an application framework for predicting vertical track irregularity, based on a real-world, large-scale dataset produced by several operating railways in China. We have conducted extensive experiments on various machine learning & ensemble learning algorithms in an effort to maximize the model's capability in capturing any irregularity. We also proposed a novel approach for handling imbalanced data in multivariate time series prediction tasks with adaptive data sampling and penalized loss. Such an approach has proven to reduce models' sensitivity to the imbalanced target domain, thus improving its performance in predicting rare extreme values.

cs.LG↗

arXiv2021

SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network

We present SpeechStew, a speech recognition model that is trained on a combination of various publicly available speech recognition datasets: AMI, Broadcast News, Common Voice, LibriSpeech, Switchboard/Fisher, Tedlium, and Wall Street Journal. SpeechStew simply mixes all of these datasets together, without any special re-weighting or re-balancing of the datasets. SpeechStew achieves SoTA or near SoTA results across a variety of tasks, without the use of an external language model. Our results include 9.0\% WER on AMI-IHM, 4.7\% WER on Switchboard, 8.3\% WER on CallHome, and 1.3\% on WSJ, which significantly outperforms prior work with strong external language models. We also demonstrate that SpeechStew learns powerful transfer learning representations. We fine-tune SpeechStew on a noisy low resource speech dataset, CHiME-6. We achieve 38.9\% WER without a language model, which compares to 38.6\% WER to a strong HMM baseline with a language model.

cs.CL↗

arXiv2021

Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction

Confidence scores are very useful for downstream applications of automatic speech recognition (ASR) systems. Recent works have proposed using neural networks to learn word or utterance confidence scores for end-to-end ASR. In those studies, word confidence by itself does not model deletions, and utterance confidence does not take advantage of word-level training signals. This paper proposes to jointly learn word confidence, word deletion, and utterance confidence. Empirical results show that multi-task learning with all three objectives improves confidence metrics (NCE, AUC, RMSE) without the need for increasing the model size of the confidence estimation module. Using the utterance-level confidence for rescoring also decreases the word error rates on Google's Voice Search and Long-tail Maps datasets by 3-5% relative, without needing a dedicated neural rescorer.

eess.AS↗

arXiv2021

Deep Latent Emotion Network for Multi-Task Learning

Feed recommendation models are widely adopted by numerous feed platforms to encourage users to explore the contents they are interested in. However, most of the current research simply focus on targeting user's preference and lack in-depth study of avoiding objectionable contents to be frequently recommended, which is a common reason that let user detest. To address this issue, we propose a Deep Latent Emotion Network (DLEN) model to extract latent probability of a user preferring a feed by modeling multiple targets with semi-supervised learning. With this method, the conflicts of different targets are successfully reduced in the training phase, which improves the training accuracy of each target effectively. Besides, by adding this latent state of user emotion to multi-target fusion, the model is capable of decreasing the probability to recommend objectionable contents to improve user retention and stay time during online testing phase. DLEN is deployed on a real-world multi-task feed recommendation scenario of Tencent QQ-Small-World with a dataset containing over a billion samples, and it exhibits a significant performance advantage over the SOTA MTL model in offline evaluation, together with a considerable increase by 3.02% in view-count and 2.63% in user stay-time in production. Complementary offline experiments of DLEN model on a public dataset also repeat improvements in various scenarios. At present, DLEN model has been successfully deployed in Tencent's feed recommendation system.

cs.AI↗

arXiv2021

CSAFL: A Clustered Semi-Asynchronous Federated Learning Framework

Federated learning (FL) is an emerging distributed machine learning paradigm that protects privacy and tackles the problem of isolated data islands. At present, there are two main communication strategies of FL: synchronous FL and asynchronous FL. The advantages of synchronous FL are that the model has high precision and fast convergence speed. However, this synchronous communication strategy has the risk that the central server waits too long for the devices, namely, the straggler effect which has a negative impact on some time-critical applications. Asynchronous FL has a natural advantage in mitigating the straggler effect, but there are threats of model quality degradation and server crash. Therefore, we combine the advantages of these two strategies to propose a clustered semi-asynchronous federated learning (CSAFL) framework. We evaluate CSAFL based on four imbalanced federated datasets in a non-IID setting and compare CSAFL to the baseline methods. The experimental results show that CSAFL significantly improves test accuracy by more than +5% on the four datasets compared to TA-FedAvg. In particular, CSAFL improves absolute test accuracy by +34.4% on non-IID FEMNIST compared to TA-FedAvg.

cs.LG↗