arXiv subjects

Jia Jia

Publications and source records attributed to Jia Jia.

71 records · Page 4Linked to original sources

arXiv2021

Potential density of projective varieties having an int-amplified endomorphism

We consider the potential density of rational points on an algebraic variety defined over a number field $K$, i.e., the property that the set of rational points of $X$ becomes Zariski dense after a finite field extension of $K$. For a non-uniruled projective variety with an int-amplified endomorphism, we show that it always satisfies potential density. When a rationally connected variety admits an int-amplified endomorphism, we prove that there exists some rational curve with a Zariski dense forward orbit, assuming the Zariski dense orbit conjecture in lower dimensions. As an application, we prove the potential density for projective varieties with int-amplified endomorphisms in dimension $\leq 3$. We also study the existence of densely many rational points with the maximal arithmetic degree over a sufficiently large number field.

math.AG↗

arXiv2021

PTeacher: a Computer-Aided Personalized Pronunciation Training System with Exaggerated Audio-Visual Corrective Feedback

Second language (L2) English learners often find it difficult to improve their pronunciations due to the lack of expressive and personalized corrective feedback. In this paper, we present Pronunciation Teacher (PTeacher), a Computer-Aided Pronunciation Training (CAPT) system that provides personalized exaggerated audio-visual corrective feedback for mispronunciations. Though the effectiveness of exaggerated feedback has been demonstrated, it is still unclear how to define the appropriate degrees of exaggeration when interacting with individual learners. To fill in this gap, we interview 100 L2 English learners and 22 professional native teachers to understand their needs and experiences. Three critical metrics are proposed for both learners and teachers to identify the best exaggeration levels in both audio and visual modalities. Additionally, we incorporate the personalized dynamic feedback mechanism given the English proficiency of learners. Based on the obtained insights, a comprehensive interactive pronunciation training course is designed to help L2 learners rectify mispronunciations in a more perceptible, understandable, and discriminative manner. Extensive user studies demonstrate that our system significantly promotes the learners' learning efficiency.

cs.HC↗

arXiv2021

Towards Multi-Scale Style Control for Expressive Speech Synthesis

This paper introduces a multi-scale speech style modeling method for end-to-end expressive speech synthesis. The proposed method employs a multi-scale reference encoder to extract both the global-scale utterance-level and the local-scale quasi-phoneme-level style features of the target speech, which are then fed into the speech synthesis model as an extension to the input phoneme sequence. During training time, the multi-scale style model could be jointly trained with the speech synthesis model in an end-to-end fashion. By applying the proposed method to style transfer task, experimental results indicate that the controllability of the multi-scale speech style model and the expressiveness of the synthesized speech are greatly improved. Moreover, by assigning different reference speeches to extraction of style on each scale, the flexibility of the proposed method is further revealed.

cs.SD↗

arXiv2020

Visual-speech Synthesis of Exaggerated Corrective Feedback

To provide more discriminative feedback for the second language (L2) learners to better identify their mispronunciation, we propose a method for exaggerated visual-speech feedback in computer-assisted pronunciation training (CAPT). The speech exaggeration is realized by an emphatic speech generation neural network based on Tacotron, while the visual exaggeration is accomplished by ADC Viseme Blending, namely increasing Amplitude of movement, extending the phone's Duration and enhancing the color Contrast. User studies show that exaggerated feedback outperforms non-exaggerated version on helping learners with pronunciation identification and pronunciation improvement.

eess.AS↗

arXiv2020

Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding

Transformer has shown promising results in many sequence to sequence transformation tasks recently. It utilizes a number of feed-forward self-attention layers to replace the recurrent neural networks (RNN) in attention-based encoder decoder (AED) architecture. Self-attention layer learns temporal dependence by incorporating sinusoidal positional embedding of tokens in a sequence for parallel computing. Quicker iteration speed in training than sequential operation of RNN can be obtained. Deeper layers of the transformer also make it perform better than RNN-based AED. However, this parallelization ability is lost when applying scheduled sampling training. Self-attention with sinusoidal positional embedding may cause performance degradations for longer sequences that have similar acoustic or semantic information at different positions as well. To address these problems, we propose to use parallel scheduled sampling (PSS) and relative positional embedding (RPE) to help the transformer generalize to unseen data. Our proposed methods achieve a 7% relative improvement for short utterances and a 70% relative gain for long utterances on a 10,000-hour Mandarin ASR task.

cs.CL↗

arXiv2020

ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unit

Dance and music are two highly correlated artistic forms. Synthesizing dance motions has attracted much attention recently. Most previous works conduct music-to-dance synthesis via directly music to human skeleton keypoints mapping. Meanwhile, human choreographers design dance motions from music in a two-stage manner: they firstly devise multiple choreographic dance units (CAUs), each with a series of dance motions, and then arrange the CAU sequence according to the rhythm, melody and emotion of the music. Inspired by these, we systematically study such two-stage choreography approach and construct a dataset to incorporate such choreography knowledge. Based on the constructed dataset, we design a two-stage music-to-dance synthesis framework ChoreoNet to imitate human choreography procedure. Our framework firstly devises a CAU prediction model to learn the mapping relationship between music and CAU sequences. Afterwards, we devise a spatial-temporal inpainting model to convert the CAU sequence into continuous dance motions. Experimental results demonstrate that the proposed ChoreoNet outperforms baseline methods (0.622 in terms of CAU BLEU score and 1.59 in terms of user study score).

cs.CV↗

arXiv2020

Speaker Independent and Multilingual/Mixlingual Speech-Driven Talking Head Generation Using Phonetic Posteriorgrams

Generating 3D speech-driven talking head has received more and more attention in recent years. Recent approaches mainly have following limitations: 1) most speaker-independent methods need handcrafted features that are time-consuming to design or unreliable; 2) there is no convincing method to support multilingual or mixlingual speech as input. In this work, we propose a novel approach using phonetic posteriorgrams (PPG). In this way, our method doesn't need hand-crafted features and is more robust to noise compared to recent approaches. Furthermore, our method can support multilingual speech as input by building a universal phoneme space. As far as we know, our model is the first to support multilingual/mixlingual speech as input with convincing results. Objective and subjective experiments have shown that our model can generate high quality animations given speech from unseen languages or speakers and be robust to noise.

eess.AS↗

arXiv2019

Mining Unfollow Behavior in Large-Scale Online Social Networks via Spatial-Temporal Interaction

Online Social Networks (OSNs) evolve through two pervasive behaviors: follow and unfollow, which respectively signify relationship creation and relationship dissolution. Researches on social network evolution mainly focus on the follow behavior, while the unfollow behavior has largely been ignored. Mining unfollow behavior is challenging because user's decision on unfollow is not only affected by the simple combination of user's attributes like informativeness and reciprocity, but also affected by the complex interaction among them. Meanwhile, prior datasets seldom contain sufficient records for inferring such complex interaction. To address these issues, we first construct a large-scale real-world Weibo dataset, which records detailed post content and relationship dynamics of 1.8 million Chinese users. Next, we define user's attributes as two categories: spatial attributes (e.g., social role of user) and temporal attributes (e.g., post content of user). Leveraging the constructed dataset, we systematically study how the interaction effects between user's spatial and temporal attributes contribute to the unfollow behavior. Afterwards, we propose a novel unified model with heterogeneous information (UMHI) for unfollow prediction. Specifically, our UMHI model: 1) captures user's spatial attributes through social network structure; 2) infers user's temporal attributes through user-posted content and unfollow history; and 3) models the interaction between spatial and temporal attributes by the nonlinear MLP layers. Comprehensive evaluations on the constructed dataset demonstrate that the proposed UMHI model outperforms baseline methods by 16.44% on average in terms of precision. In addition, factor analyses verify that both spatial attributes and temporal attributes are essential for mining unfollow behavior.

cs.SI↗

arXiv2019

Understanding the Teaching Styles by an Attention based Multi-task Cross-media Dimensional modelling

Teaching style plays an influential role in helping students to achieve academic success. In this paper, we explore a new problem of effectively understanding teachers' teaching styles. Specifically, we study 1) how to quantitatively characterize various teachers' teaching styles for various teachers and 2) how to model the subtle relationship between cross-media teaching related data (speech, facial expressions and body motions, content et al.) and teaching styles. Using the adjectives selected from more than 10,000 feedback questionnaires provided by an educational enterprise, a novel concept called Teaching Style Semantic Space (TSSS) is developed based on the pleasure-arousal dimensional theory to describe teaching styles quantitatively and comprehensively. Then a multi-task deep learning based model, Attention-based Multi-path Multi-task Deep Neural Network (AMMDNN), is proposed to accurately and robustly capture the internal correlations between cross-media features and TSSS. Based on the benchmark dataset, we further develop a comprehensive data set including 4,541 full-annotated cross-modality teaching classes. Our experimental results demonstrate that the proposed AMMDNN outperforms (+0.0842 in terms of the concordance correlation coefficient (CCC) on average) baseline methods. To further demonstrate the advantages of the proposed TSSS and our model, several interesting case studies are carried out, such as teaching styles comparison among different teachers and courses, and leveraging the proposed method for teaching quality analysis.

cs.MM↗

arXiv2019

Efficient Electrocatalytic Reduction of CO2 by Nitrogen-Doped Nanoporous Carbon-Carbon Nanotube Membranes - A Step Towards the Electrochemical CO2 Refinery

The search for earth abundant, efficient and stable electrocatalysts that can enable the chemical reduction of CO2 to value-added chemicals and fuels at an industrially relevant scale, is a high priority for the development of a global network of renewable energy conversion and storage systems that can meaningfully impact greenhouse gas induced climate change. Here we introduce a straightforward, low cost, scalable and technologically relevant method to manufacture an all-carbon, electroactive, nitrogen-doped nanoporous carbon-carbon nanotube composite membrane, dubbed "HNCM-CNT". The membrane is demonstrated to function as a binder-free, high-performance electrode for the electrocatalytic reduction of CO2 to formate. The Faradaic efficiency for the production of formate is 81%. Furthermore, the robust structural and electrochemical properties of the membrane endow it with excellent long-term stability.

physics.chem-ph↗

arXiv2019

An Online Attention-based Model for Speech Recognition

Attention-based end-to-end models such as Listen, Attend and Spell (LAS), simplify the whole pipeline of traditional automatic speech recognition (ASR) systems and become popular in the field of speech recognition. In previous work, researchers have shown that such architectures can acquire comparable results to state-of-the-art ASR systems, especially when using a bidirectional encoder and global soft attention (GSA) mechanism. However, bidirectional encoder and GSA are two obstacles for real-time speech recognition. In this work, we aim to stream LAS baseline by removing the above two obstacles. On the encoder side, we use a latency-controlled (LC) bidirectional structure to reduce the delay of forward computation. Meanwhile, an adaptive monotonic chunk-wise attention (AMoChA) mechanism is proposed to replace GSA for the calculation of attention weight distribution. Furthermore, we propose two methods to alleviate the huge performance degradation when combining LC and AMoChA. Finally, we successfully acquire an online LAS model, LC-AMoChA, which has only 3.5% relative performance reduction to LAS baseline on our internal Mandarin corpus.

cs.CL↗

arXiv2019

Exploring RNN-Transducer for Chinese Speech Recognition

End-to-end approaches have drawn much attention recently for significantly simplifying the construction of an automatic speech recognition (ASR) system. RNN transducer (RNN-T) is one of the popular end-to-end methods. Previous studies have shown that RNN-T is difficult to train and a very complex training process is needed for a reasonable performance. In this paper, we explore RNN-T for a Chinese large vocabulary continuous speech recognition (LVCSR) task and aim to simplify the training process while maintaining performance. First, a new strategy of learning rate decay is proposed to accelerate the model convergence. Second, we find that adding convolutional layers at the beginning of the network and using ordered data can discard the pre-training process of the encoder without loss of performance. Besides, we design experiments to find a balance among the usage of GPU memory, training circle and model performance. Finally, we achieve 16.9% character error rate (CER) on our test set which is 2% absolute improvement from a strong BLSTM CE system with language model trained on the same text corpus.

cs.CL↗

arXiv2019

Modality Attention for End-to-End Audio-visual Speech Recognition

Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance. Our method is realized using state-of-the-art sequence-to-sequence (Seq2seq) architectures. Experimental results show that relative improvements from 2% up to 36% over the auditory modality alone are obtained depending on the different signal-to-noise-ratio (SNR). Compared to the traditional feature concatenation methods, our proposed approach can achieve better recognition performance under both clean and noisy conditions. We believe modality attention based end-to-end method can be easily generalized to other multimodal tasks with correlated information.

cs.CL↗

arXiv2018

Automated segmentaiton and classification of arterioles and venules using Cascading Dilated Convolutional Neural Networks

The change of retinal vasculature is an early sign of many vascular and systematic diseases, such as diabetes and hypertension. Different behaviors of retinal arterioles and venules form an important metric to measure the disease severity. Therefore, an accurate classification of arterioles and venules is of great necessity. In this work, we propose a novel architecture of deep convolutional neural network for segmenting and classifying arterioles and venules on retinal fundus images. This network takes the original color fundus image as inputs and multi-class labels as outputs. We adopt the encoding-decoding structure (Unet) as the backbone network of our proposed model. To improve the classification accuracy, we develop a special encoding path that couples InceptionV4 modules and Cascading Dilated Convolutions (CDCs) on top of the backbone network. The model is thus able to extract and fuse high-level semantic features from multi-scale receptive fields. The proposed method has outperformed the previous state-of-the-art method on DRIVE dataset with an accuracy of 0.955 $\pm$ 0.002.

cs.CV↗

arXiv2017

A Novel Method of Subgroup Identification by Combining Virtual Twins with GUIDE (VG) for Development of Precision Medicines

A lack of understanding of human biology creates a hurdle for the development of precision medicines. To overcome this hurdle we need to better understand the potential synergy between a given investigational treatment (vs. placebo or active control) and various demographic or genetic factors, disease history and severity, etc., with the goal of identifying those patients at increased risk of exhibiting clinically meaningful treatment benefit. For this reason, we propose the VG method, which combines the idea of an individual treatment effect (ITE) from Virtual Twins (Foster, et al., 2011) with the unbiased variable selection and cutoff value determination algorithm from GUIDE (Loh, et al., 2015). Simulation results show the VG method has less variable selection bias than Virtual Twins and higher statistical power than GUIDE Interaction in the presence of prognostic variables with strong treatment effects. Type I error and predictive performance of Virtual Twins, GUIDE and VG are compared through the use of simulation studies. Results obtained after retrospectively applying VG to data from a clinical trial also are discussed.

stat.AP↗

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↗

arXiv2014

Modeling Emotion Influence from Images in Social Networks

Images become an important and prevalent way to express users' activities, opinions and emotions. In a social network, individual emotions may be influenced by others, in particular by close friends. We focus on understanding how users embed emotions into the images they uploaded to the social websites and how social influence plays a role in changing users' emotions. We first verify the existence of emotion influence in the image networks, and then propose a probabilistic factor graph based emotion influence model to answer the questions of "who influences whom". Employing a real network from Flickr as experimental data, we study the effectiveness of factors in the proposed model with in-depth data analysis. Our experiments also show that our model, by incorporating the emotion influence, can significantly improve the accuracy (+5%) for predicting emotions from images. Finally, a case study is used as the anecdotal evidence to further demonstrate the effectiveness of the proposed model.

cs.SI↗