arXiv subjects

Yuan Jiang

Publications and source records attributed to Yuan Jiang.

At least 55 records · Page 3Linked to original sources

arXiv2022

Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Models

Neural network models have achieved state-of-the-art performance on grapheme-to-phoneme (G2P) conversion. However, their performance relies on large-scale pronunciation dictionaries, which may not be available for a lot of languages. Inspired by the success of the pre-trained language model BERT, this paper proposes a pre-trained grapheme model called grapheme BERT (GBERT), which is built by self-supervised training on a large, language-specific word list with only grapheme information. Furthermore, two approaches are developed to incorporate GBERT into the state-of-the-art Transformer-based G2P model, i.e., fine-tuning GBERT or fusing GBERT into the Transformer model by attention. Experimental results on the Dutch, Serbo-Croatian, Bulgarian and Korean datasets of the SIGMORPHON 2021 G2P task confirm the effectiveness of our GBERT-based G2P models under both medium-resource and low-resource data conditions.

cs.CL↗

arXiv2021

A Simple Approach for Non-stationary Linear Bandits

This paper investigates the problem of non-stationary linear bandits, where the unknown regression parameter is evolving over time. Existing studies develop various algorithms and show that they enjoy an $\widetilde{\mathcal{O}}(T^{2/3}P_T^{1/3})$ dynamic regret, where $T$ is the time horizon and $P_T$ is the path-length that measures the fluctuation of the evolving unknown parameter. In this paper, we discover that a serious technical flaw makes their results ungrounded, and then present a fix, which gives an $\widetilde{\mathcal{O}}(T^{3/4}P_T^{1/4})$ dynamic regret without modifying original algorithms. Furthermore, we demonstrate that instead of using sophisticated mechanisms, such as sliding window or weighted penalty, a simple restarted strategy is sufficient to attain the same regret guarantee. Specifically, we design an UCB-type algorithm to balance exploitation and exploration, and restart it periodically to handle the drift of unknown parameters. Our approach enjoys an $\widetilde{\mathcal{O}}(T^{3/4}P_T^{1/4})$ dynamic regret. Note that to achieve this bound, the algorithm requires an oracle knowledge of the path-length $P_T$. Combining the bandits-over-bandits mechanism by treating our algorithm as the base learner, we can further achieve the same regret bound in a parameter-free way. Empirical studies also validate the effectiveness of our approach.

cs.LG↗

arXiv2021

LIFE: Learning Individual Features for Multivariate Time Series Prediction with Missing Values

Multivariate time series (MTS) prediction is ubiquitous in real-world fields, but MTS data often contains missing values. In recent years, there has been an increasing interest in using end-to-end models to handle MTS with missing values. To generate features for prediction, existing methods either merge all input dimensions of MTS or tackle each input dimension independently. However, both approaches are hard to perform well because the former usually produce many unreliable features and the latter lacks correlated information. In this paper, we propose a Learning Individual Features (LIFE) framework, which provides a new paradigm for MTS prediction with missing values. LIFE generates reliable features for prediction by using the correlated dimensions as auxiliary information and suppressing the interference from uncorrelated dimensions with missing values. Experiments on three real-world data sets verify the superiority of LIFE to existing state-of-the-art models.

cs.LG↗

arXiv2021

VulSPG: Vulnerability detection based on slice property graph representation learning

Vulnerability detection is an important issue in software security. Although various data-driven vulnerability detection methods have been proposed, the task remains challenging since the diversity and complexity of real-world vulnerable code in syntax and semantics make it difficult to extract vulnerable features with regular deep learning models, especially in analyzing a large program. Moreover, the fact that real-world vulnerable codes contain a lot of redundant information unrelated to vulnerabilities will further aggravate the above problem. To mitigate such challenges, we define a novel code representation named Slice Property Graph (SPG), and then propose VulSPG, a new vulnerability detection approach using the improved R-GCN model with triple attention mechanism to identify potential vulnerabilities in SPG. Our approach has at least two advantages over other methods. First, our proposed SPG can reflect the rich semantics and explicit structural information that may be relevance to vulnerabilities, while eliminating as much irrelevant information as possible to reduce the complexity of graph. Second, VulSPG incorporates triple attention mechanism in R-GCNs to achieve more effective learning of vulnerability patterns from SPG. We have extensively evaluated VulSPG on two large-scale datasets with programs from SARD and real-world projects. Experimental results prove the effectiveness and efficiency of VulSPG.

cs.CR↗

arXiv2021

Imitation Learning from Pixel-Level Demonstrations by HashReward

One of the key issues for imitation learning lies in making policy learned from limited samples to generalize well in the whole state-action space. This problem is much more severe in high-dimensional state environments, such as game playing with raw pixel inputs. Under this situation, even state-of-the-art adversary-based imitation learning algorithms fail. Through empirical studies, we find that the main cause lies in the failure of training a powerful discriminator to generate meaningful rewards in high-dimensional environments. Although it seems that dimensionality reduction can help, a straightforward application of off-the-shelf methods cannot achieve good performance. In this work, we show in theory that the balance between dimensionality reduction and discriminative training is essential for effective learning. To achieve this target, we propose HashReward, which utilizes the idea of supervised hashing to realize such an ideal balance. Experimental results show that HashReward could outperform state-of-the-art methods for a large gap under the challenging high-dimensional environments.

cs.LG↗

arXiv2021

The Design of the User Interfaces for Privacy Enhancements for Android

We present the design and design rationale for the user interfaces for Privacy Enhancements for Android (PE for Android). These UIs are built around two core ideas, namely that developers should explicitly declare the purpose of why sensitive data is being used, and these permission-purpose pairs should be split by first party and third party uses. We also present a taxonomy of purposes and ways of how these ideas can be deployed in the existing Android ecosystem.

cs.CR↗

arXiv2021

Semi-Supervised Multi-Modal Multi-Instance Multi-Label Deep Network with Optimal Transport

Complex objects are usually with multiple labels, and can be represented by multiple modal representations, e.g., the complex articles contain text and image information as well as multiple annotations. Previous methods assume that the homogeneous multi-modal data are consistent, while in real applications, the raw data are disordered, e.g., the article constitutes with variable number of inconsistent text and image instances. Therefore, Multi-modal Multi-instance Multi-label (M3) learning provides a framework for handling such task and has exhibited excellent performance. However, M3 learning is facing two main challenges: 1) how to effectively utilize label correlation; 2) how to take advantage of multi-modal learning to process unlabeled instances. To solve these problems, we first propose a novel Multi-modal Multi-instance Multi-label Deep Network (M3DN), which considers M3 learning in an end-to-end multi-modal deep network and utilizes consistency principle among different modal bag-level predictions. Based on the M3DN, we learn the latent ground label metric with the optimal transport. Moreover, we introduce the extrinsic unlabeled multi-modal multi-instance data, and propose the M3DNS, which considers the instance-level auto-encoder for single modality and modified bag-level optimal transport to strengthen the consistency among modalities. Thereby M3DNS can better predict label and exploit label correlation simultaneously. Experiments on benchmark datasets and real world WKG Game-Hub dataset validate the effectiveness of the proposed methods.

cs.LG↗

arXiv2020

Provably Robust Metric Learning

Metric learning is an important family of algorithms for classification and similarity search, but the robustness of learned metrics against small adversarial perturbations is less studied. In this paper, we show that existing metric learning algorithms, which focus on boosting the clean accuracy, can result in metrics that are less robust than the Euclidean distance. To overcome this problem, we propose a novel metric learning algorithm to find a Mahalanobis distance that is robust against adversarial perturbations, and the robustness of the resulting model is certifiable. Experimental results show that the proposed metric learning algorithm improves both certified robust errors and empirical robust errors (errors under adversarial attacks). Furthermore, unlike neural network defenses which usually encounter a trade-off between clean and robust errors, our method does not sacrifice clean errors compared with previous metric learning methods. Our code is available at https://github.com/wangwllu/provably_robust_metric_learning.

cs.LG↗

arXiv2020

Spanning Attack: Reinforce Black-box Attacks with Unlabeled Data

Adversarial black-box attacks aim to craft adversarial perturbations by querying input-output pairs of machine learning models. They are widely used to evaluate the robustness of pre-trained models. However, black-box attacks often suffer from the issue of query inefficiency due to the high dimensionality of the input space, and therefore incur a false sense of model robustness. In this paper, we relax the conditions of the black-box threat model, and propose a novel technique called the spanning attack. By constraining adversarial perturbations in a low-dimensional subspace via spanning an auxiliary unlabeled dataset, the spanning attack significantly improves the query efficiency of a wide variety of existing black-box attacks. Extensive experiments show that the proposed method works favorably in both soft-label and hard-label black-box attacks. Our code is available at https://github.com/wangwllu/spanning_attack.

cs.LG↗

arXiv2020

Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody Transfer

With the development of automatic speech recognition (ASR) and text-to-speech synthesis (TTS) technique, it's intuitive to construct a voice conversion system by cascading an ASR and TTS system. In this paper, we present a ASR-TTS method for voice conversion, which used iFLYTEK ASR engine to transcribe the source speech into text and a Transformer TTS model with WaveNet vocoder to synthesize the converted speech from the decoded text. For the TTS model, we proposed to use a prosody code to describe the prosody information other than text and speaker information contained in speech. A prosody encoder is used to extract the prosody code. During conversion, the source prosody is transferred to converted speech by conditioning the Transformer TTS model with its code. Experiments were conducted to demonstrate the effectiveness of our proposed method. Our system also obtained the best naturalness and similarity in the mono-lingual task of Voice Conversion Challenge 2020.

eess.AS↗

arXiv2020

ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech

Automatic speaker verification (ASV) is one of the most natural and convenient means of biometric person recognition. Unfortunately, just like all other biometric systems, ASV is vulnerable to spoofing, also referred to as "presentation attacks." These vulnerabilities are generally unacceptable and call for spoofing countermeasures or "presentation attack detection" systems. In addition to impersonation, ASV systems are vulnerable to replay, speech synthesis, and voice conversion attacks. The ASVspoof 2019 edition is the first to consider all three spoofing attack types within a single challenge. While they originate from the same source database and same underlying protocol, they are explored in two specific use case scenarios. Spoofing attacks within a logical access (LA) scenario are generated with the latest speech synthesis and voice conversion technologies, including state-of-the-art neural acoustic and waveform model techniques. Replay spoofing attacks within a physical access (PA) scenario are generated through carefully controlled simulations that support much more revealing analysis than possible previously. Also new to the 2019 edition is the use of the tandem detection cost function metric, which reflects the impact of spoofing and countermeasures on the reliability of a fixed ASV system. This paper describes the database design, protocol, spoofing attack implementations, and baseline ASV and countermeasure results. It also describes a human assessment on spoofed data in logical access. It was demonstrated that the spoofing data in the ASVspoof 2019 database have varied degrees of perceived quality and similarity to the target speakers, including spoofed data that cannot be differentiated from bona-fide utterances even by human subjects.

eess.AS↗

arXiv2020

Soft Gradient Boosting Machine

Gradient Boosting Machine has proven to be one successful function approximator and has been widely used in a variety of areas. However, since the training procedure of each base learner has to take the sequential order, it is infeasible to parallelize the training process among base learners for speed-up. In addition, under online or incremental learning settings, GBMs achieved sub-optimal performance due to the fact that the previously trained base learners can not adapt with the environment once trained. In this work, we propose the soft Gradient Boosting Machine (sGBM) by wiring multiple differentiable base learners together, by injecting both local and global objectives inspired from gradient boosting, all base learners can then be jointly optimized with linear speed-up. When using differentiable soft decision trees as base learner, such device can be regarded as an alternative version of the (hard) gradient boosting decision trees with extra benefits. Experimental results showed that, sGBM enjoys much higher time efficiency with better accuracy, given the same base learner in both on-line and off-line settings.

cs.LG↗

arXiv2020

Sequence-to-Sequence Acoustic Modeling for Voice Conversion

In this paper, a neural network named Sequence-to-sequence ConvErsion NeTwork (SCENT) is presented for acoustic modeling in voice conversion. At training stage, a SCENT model is estimated by aligning the feature sequences of source and target speakers implicitly using attention mechanism. At conversion stage, acoustic features and durations of source utterances are converted simultaneously using the unified acoustic model. Mel-scale spectrograms are adopted as acoustic features which contain both excitation and vocal tract descriptions of speech signals. The bottleneck features extracted from source speech using an automatic speech recognition (ASR) model are appended as auxiliary input. A WaveNet vocoder conditioned on Mel-spectrograms is built to reconstruct waveforms from the outputs of the SCENT model. It is worth noting that our proposed method can achieve appropriate duration conversion which is difficult in conventional methods. Experimental results show that our proposed method obtained better objective and subjective performance than the baseline methods using Gaussian mixture models (GMM) and deep neural networks (DNN) as acoustic models. This proposed method also outperformed our previous work which achieved the top rank in Voice Conversion Challenge 2018. Ablation tests further confirmed the effectiveness of several components in our proposed method.

cs.SD↗

arXiv2019

Multi-Label Learning with Deep Forest

In multi-label learning, each instance is associated with multiple labels and the crucial task is how to leverage label correlations in building models. Deep neural network methods usually jointly embed the feature and label information into a latent space to exploit label correlations. However, the success of these methods highly depends on the precise choice of model depth. Deep forest is a recent deep learning framework based on tree model ensembles, which does not rely on backpropagation. We consider the advantages of deep forest models are very appropriate for solving multi-label problems. Therefore we design the Multi-Label Deep Forest (MLDF) method with two mechanisms: measure-aware feature reuse and measure-aware layer growth. The measure-aware feature reuse mechanism reuses the good representation in the previous layer guided by confidence. The measure-aware layer growth mechanism ensures MLDF gradually increase the model complexity by performance measure. MLDF handles two challenging problems at the same time: one is restricting the model complexity to ease the overfitting issue; another is optimizing the performance measure on user's demand since there are many different measures in the multi-label evaluation. Experiments show that our proposal not only beats the compared methods over six measures on benchmark datasets but also enjoys label correlation discovery and other desired properties in multi-label learning.

cs.LG↗

arXiv2019

End-to-End Emotional Speech Synthesis Using Style Tokens and Semi-Supervised Training

This paper proposes an end-to-end emotional speech synthesis (ESS) method which adopts global style tokens (GSTs) for semi-supervised training. This model is built based on the GST-Tacotron framework. The style tokens are defined to present emotion categories. A cross entropy loss function between token weights and emotion labels is designed to obtain the interpretability of style tokens utilizing the small portion of training data with emotion labels. Emotion recognition experiments confirm that this method can achieve one-to-one correspondence between style tokens and emotion categories effectively. Objective and subjective evaluation results show that our model outperforms the conventional Tacotron model for ESS when only 5\% of training data has emotion labels. Its subjective performance is close to the Tacotron model trained using all emotion labels.

eess.AS↗

arXiv2018

Improving Sequence-to-Sequence Acoustic Modeling by Adding Text-Supervision

This paper presents methods of making using of text supervision to improve the performance of sequence-to-sequence (seq2seq) voice conversion. Compared with conventional frame-to-frame voice conversion approaches, the seq2seq acoustic modeling method proposed in our previous work achieved higher naturalness and similarity. In this paper, we further improve its performance by utilizing the text transcriptions of parallel training data. First, a multi-task learning structure is designed which adds auxiliary classifiers to the middle layers of the seq2seq model and predicts linguistic labels as a secondary task. Second, a data-augmentation method is proposed which utilizes text alignment to produce extra parallel sequences for model training. Experiments are conducted to evaluate our proposed method with training sets at different sizes. Experimental results show that the multi-task learning with linguistic labels is effective at reducing the errors of seq2seq voice conversion. The data-augmentation method can further improve the performance of seq2seq voice conversion when only 50 or 100 training utterances are available.

cs.SD↗

arXiv2018

Impact of Land Use on the DOM Composition in Different Seasons in a Subtropical River Flowing through the Region Undergoing Rapid Urbanization

The dissolved organic matter (DOM) composition in river ecosystems could reflect the human impacts on the river ecosystem, and plays an important role in the carbon cycling process. We collected water and phytoplankton samples at 107 sites in the Dongjiang River in two seasons to assess the impact of the sub-catchments land use structure on the DOM composition. The results showed that (1) the forested sub-catchments had higher humic-like C1 (16.45%) and C2 (25.04%) and lower protein-like C3 (22.57%) and C4 (35.95%) than urbanized and mixed forest-agriculture sub-catchments, while the urbanized sub-catchments showed an inverse trend (4.54%, 15.51%, 33.97% and 45.98%, respectively). (2) The significant variation in the proportion of C1 and C4 between the dry and rainy seasons was recorded in both the forested and the mixed forest-agriculture sub-catchments (p<0.01), but only C4 showed an obvious seasonal variation in the urbanized sub-catchments (p<0.01). While the DOM composition was mainly related to the proportion of urbanized land and forested land year-round (p<0.01), it had stronger correlation with forested land in the dry season and urbanized land in the rainy season. (3) No significant correlation between the DOM composition and the agricultural land proportion was found in either season (p>0.05). Our findings indicated that the DOM composition was strongly dependent on the land use structure of the sub-catchments and varied seasonally, but the seasonal variation pattern could be disturbed by human activities in the extensively urbanized catchments. Notably, the higher C4 proportion compared with those in temperate rivers implied a larger amount of CO2 released from the subtropical rivers into the atmosphere when considering bioavailability.

q-bio.PE↗

arXiv2017

Early monsoon drought and mid-summer vapor pressure deficit induce growth cessation of lower margin Picea crassifolia

Extreme climatic events have been shown to be strong drivers of tree growth, forest dynamics, and range contraction. Here we study the climatic drivers of Picea crassifolia Kom., an endemic to northwest China where climate has significantly warmed. Picea crassifolia was sampled from its lower distributional margin to its upper distributional margin on the Helan Mountains to test the hypothesis that 1) growth at the upper limit is limited by cool temperatures and 2) is limited by drought at its lower limit. We found that trees at the lower distributional margin have experienced a higher rate of stem-growth cessation events since 2001 compared to trees at other elevations. While all populations have a similar climatic sensitivity, stem-growth cessation events in trees at lower distributional margin appear to be driven by low precipitation in June as the monsoon begins to deliver moisture to the region. Evidence indicates that mid-summer (July) vapor pressure deficit (VPD) exacerbates the frequency of these events. These data and our analysis makes it evident that an increase in severity and frequency of drought early in the monsoon season could increase the frequency and severity of stem-growth cessation in Picea crassifolia trees at lower elevations. Increases in VPD and warming would likely exacerbate the growth stress of this species on Helan Mountain. Hypothetically, if the combinations of low moisture and increased VPD stress becomes more common, the mortality rate of lower distributional margin trees could increase, especially of those that are already experiencing events of temporary growth cessation.

q-bio.QM↗