arXiv subjects

Jun Du

Publications and source records attributed to Jun Du.

At least 163 records · Page 9Linked to original sources

arXiv2020

Stroke Constrained Attention Network for Online Handwritten Mathematical Expression Recognition

In this paper, we propose a novel stroke constrained attention network (SCAN) which treats stroke as the basic unit for encoder-decoder based online handwritten mathematical expression recognition (HMER). Unlike previous methods which use trace points or image pixels as basic units, SCAN makes full use of stroke-level information for better alignment and representation. The proposed SCAN can be adopted in both single-modal (online or offline) and multi-modal HMER. For single-modal HMER, SCAN first employs a CNN-GRU encoder to extract point-level features from input traces in online mode and employs a CNN encoder to extract pixel-level features from input images in offline mode, then use stroke constrained information to convert them into online and offline stroke-level features. Using stroke-level features can explicitly group points or pixels belonging to the same stroke, therefore reduces the difficulty of symbol segmentation and recognition via the decoder with attention mechanism. For multi-modal HMER, other than fusing multi-modal information in decoder, SCAN can also fuse multi-modal information in encoder by utilizing the stroke based alignments between online and offline modalities. The encoder fusion is a better way for combining multi-modal information as it implements the information interaction one step before the decoder fusion so that the advantages of multiple modalities can be exploited earlier and more adequately when training the encoder-decoder model. Evaluated on a benchmark published by CROHME competition, the proposed SCAN achieves the state-of-the-art performance.

cs.CV↗

arXiv2020

An Adaptive X-vector Model for Text-independent Speaker Verification

In this paper, adaptive mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, adaptive convolutional neural networks (ACNNs) are employed in frame-level embedding layers, where the parameters of the convolution filters are adjusted based on the input features. Compared with conventional CNNs, ACNNs have more flexibility in capturing speaker information. Moreover, we replace conventional batch normalization (BN) with adaptive batch normalization (ABN). By dynamically generating the scaling and shifting parameters in BN, ABN adapts models to the acoustic variability arising from various factors such as channel and environmental noises. Finally, we incorporate these two methods to further improve performance. Experiments are carried out on the speaker in the wild (SITW) and VOiCES databases. The results demonstrate that the proposed methods significantly outperform the original x-vector approach.

eess.AS↗

arXiv2020

Attentive batch normalization for lstm-based acoustic modeling of speech recognition

Batch normalization (BN) is an effective method to accelerate model training and improve the generalization performance of neural networks. In this paper, we propose an improved batch normalization technique called attentive batch normalization (ABN) in Long Short Term Memory (LSTM) based acoustic modeling for automatic speech recognition (ASR). In the proposed method, an auxiliary network is used to dynamically generate the scaling and shifting parameters in batch normalization, and attention mechanisms are introduced to improve their regularized performance. Furthermore, two schemes, frame-level and utterance-level ABN, are investigated. We evaluate our proposed methods on Mandarin and Uyghur ASR tasks, respectively. The experimental results show that the proposed ABN greatly improves the performance of batch normalization in terms of transcription accuracy for both languages.

eess.AS↗

arXiv2019

Attention-based gated scaling adaptative acoustic model for ctc-based speech recognition

In this paper, we propose a novel adaptive technique that uses an attention-based gated scaling (AGS) scheme to improve deep feature learning for connectionist temporal classification (CTC) acoustic modeling. In AGS, the outputs of each hidden layer of the main network are scaled by an auxiliary gate matrix extracted from the lower layer by using attention mechanisms. Furthermore, the auxiliary AGS layer and the main network are jointly trained without requiring second-pass model training or additional speaker information, such as speaker code. On the Mandarin AISHELL-1 datasets, the proposed AGS yields a 7.94% character error rate (CER). To the best of our knowledge, this result is the best recognition accuracy achieved on this dataset by using an end-to-end framework.

eess.AS↗

arXiv2019

Speaker detection in the wild: Lessons learned from JSALT 2019

This paper presents the problems and solutions addressed at the JSALT workshop when using a single microphone for speaker detection in adverse scenarios. The main focus was to tackle a wide range of conditions that go from meetings to wild speech. We describe the research threads we explored and a set of modules that was successful for these scenarios. The ultimate goal was to explore speaker detection; but our first finding was that an effective diarization improves detection, and not having a diarization stage impoverishes the performance. All the different configurations of our research agree on this fact and follow a main backbone that includes diarization as a previous stage. With this backbone, we analyzed the following problems: voice activity detection, how to deal with noisy signals, domain mismatch, how to improve the clustering; and the overall impact of previous stages in the final speaker detection. In this paper, we show partial results for speaker diarizarion to have a better understanding of the problem and we present the final results for speaker detection.

eess.AS↗

arXiv2019

Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition

Recently, the hybrid convolutional neural network hidden Markov model (CNN-HMM) has been introduced for offline handwritten Chinese text recognition (HCTR) and has achieved state-of-the-art performance. However, modeling each of the large vocabulary of Chinese characters with a uniform and fixed number of hidden states requires high memory and computational costs and makes the tens of thousands of HMM state classes confusing. Another key issue of CNN-HMM for HCTR is the diversified writing style, which leads to model strain and a significant performance decline for specific writers. To address these issues, we propose a writer-aware CNN based on parsimonious HMM (WCNN-PHMM). First, PHMM is designed using a data-driven state-tying algorithm to greatly reduce the total number of HMM states, which not only yields a compact CNN by state sharing of the same or similar radicals among different Chinese characters but also improves the recognition accuracy due to the more accurate modeling of tied states and the lower confusion among them. Second, WCNN integrates each convolutional layer with one adaptive layer fed by a writer-dependent vector, namely, the writer code, to extract the irrelevant variability in writer information to improve recognition performance. The parameters of writer-adaptive layers are jointly optimized with other network parameters in the training stage, while a multiple-pass decoding strategy is adopted to learn the writer code and generate recognition results. Validated on the ICDAR 2013 competition of CASIA-HWDB database, the more compact WCNN-PHMM of a 7360-class vocabulary can achieve a relative character error rate (CER) reduction of 16.6% over the conventional CNN-HMM without considering language modeling. By adopting a powerful hybrid language model (N-gram language model and recurrent neural network language model), the CER of WCNN-PHMM is reduced to 3.17%.

cs.CV↗

arXiv2019

Adaptive Period Embedding for Representing Oriented Objects in Aerial Images

We propose a novel method for representing oriented objects in aerial images named Adaptive Period Embedding (APE). While traditional object detection methods represent object with horizontal bounding boxes, the objects in aerial images are oritented. Calculating the angle of object is an yet challenging task. While almost all previous object detectors for aerial images directly regress the angle of objects, they use complex rules to calculate the angle, and their performance is limited by the rule design. In contrast, our method is based on the angular periodicity of oriented objects. The angle is represented by two two-dimensional periodic vectors whose periods are different, the vector is continuous as shape changes. The label generation rule is more simple and reasonable compared with previous methods. The proposed method is general and can be applied to other oriented detector. Besides, we propose a novel IoU calculation method for long objects named length independent IoU (LIIoU). We intercept part of the long side of the target box to get the maximum IoU between the proposed box and the intercepted target box. Thereby, some long boxes will have corresponding positive samples. Our method reaches the 1st place of DOAI2019 competition task1 (oriented object) held in workshop on Detecting Objects in Aerial Images in conjunction with IEEE CVPR 2019.

cs.CV↗

arXiv2019

The Second DIHARD Diarization Challenge: Dataset, task, and baselines

This paper introduces the second DIHARD challenge, the second in a series of speaker diarization challenges intended to improve the robustness of diarization systems to variation in recording equipment, noise conditions, and conversational domain. The challenge comprises four tracks evaluating diarization performance under two input conditions (single channel vs. multi-channel) and two segmentation conditions (diarization from a reference speech segmentation vs. diarization from scratch). In order to prevent participants from overtuning to a particular combination of recording conditions and conversational domain, recordings are drawn from a variety of sources ranging from read audiobooks to meeting speech, to child language acquisition recordings, to dinner parties, to web video. We describe the task and metrics, challenge design, datasets, and baseline systems for speech enhancement, speech activity detection, and diarization.

eess.AS↗

arXiv2019

Attention Based Fully Convolutional Network for Speech Emotion Recognition

Speech emotion recognition is a challenging task for three main reasons: 1) human emotion is abstract, which means it is hard to distinguish; 2) in general, human emotion can only be detected in some specific moments during a long utterance; 3) speech data with emotional labeling is usually limited. In this paper, we present a novel attention based fully convolutional network for speech emotion recognition. We employ fully convolutional network as it is able to handle variable-length speech, free of the demand of segmentation to keep critical information not lost. The proposed attention mechanism can make our model be aware of which time-frequency region of speech spectrogram is more emotion-relevant. Considering limited data, the transfer learning is also adapted to improve the accuracy. Especially, it's interesting to observe obvious improvement obtained with natural scene image based pre-trained model. Validated on the publicly available IEMOCAP corpus, the proposed model outperformed the state-of-the-art methods with a weighted accuracy of 70.4% and an unweighted accuracy of 63.9% respectively.

cs.SD↗

arXiv2019

Multi-Task Learning with High-Order Statistics for X-vector based Text-Independent Speaker Verification

The x-vector based deep neural network (DNN) embedding systems have demonstrated effectiveness for text-independent speaker verification. This paper presents a multi-task learning architecture for training the speaker embedding DNN with the primary task of classifying the target speakers, and the auxiliary task of reconstructing the first- and higher-order statistics of the original input utterance. The proposed training strategy aggregates both the supervised and unsupervised learning into one framework to make the speaker embeddings more discriminative and robust. Experiments are carried out using the NIST SRE16 evaluation dataset and the VOiCES dataset. The results demonstrate that our proposed method outperforms the original x-vector approach with very low additional complexity added.

eess.AS↗

arXiv2019

Deep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification

In this paper, gating mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, a gated convolution neural network (GCNN) is employed for modeling the frame-level embedding layers. Compared with the time-delay DNN (TDNN), the GCNN can obtain more expressive frame-level representations through carefully designed memory cell and gating mechanisms. Moreover, we propose a novel gated-attention statistics pooling strategy in which the attention scores are shared with the output gate. The gated-attention statistics pooling combines both gating and attention mechanisms into one framework; therefore, we can capture more useful information in the temporal pooling layer. Experiments are carried out using the NIST SRE16 and SRE18 evaluation datasets. The results demonstrate the effectiveness of the GCNN and show that the proposed gated-attention statistics pooling can further improve the performance.

eess.AS↗

arXiv2019

Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition

Automatic emotion recognition (AER) is a challenging task due to the abstract concept and multiple expressions of emotion. Although there is no consensus on a definition, human emotional states usually can be apperceived by auditory and visual systems. Inspired by this cognitive process in human beings, it's natural to simultaneously utilize audio and visual information in AER. However, most traditional fusion approaches only build a linear paradigm, such as feature concatenation and multi-system fusion, which hardly captures complex association between audio and video. In this paper, we introduce factorized bilinear pooling (FBP) to deeply integrate the features of audio and video. Specifically, the features are selected through the embedded attention mechanism from respective modalities to obtain the emotion-related regions. The whole pipeline can be completed in a neural network. Validated on the AFEW database of the audio-video sub-challenge in EmotiW2018, the proposed approach achieves an accuracy of 62.48%, outperforming the state-of-the-art result.

cs.LG↗

arXiv2018

TextMountain: Accurate Scene Text Detection via Instance Segmentation

In this paper, we propose a novel scene text detection method named TextMountain. The key idea of TextMountain is making full use of border-center information. Different from previous works that treat center-border as a binary classification problem, we predict text center-border probability (TCBP) and text center-direction (TCD). The TCBP is just like a mountain whose top is text center and foot is text border. The mountaintop can separate text instances which cannot be easily achieved using semantic segmentation map and its rising direction can plan a road to top for each pixel on mountain foot at the group stage. The TCD helps TCBP learning better. Our label rules will not lead to the ambiguous problem with the transformation of angle, so the proposed method is robust to multi-oriented text and can also handle well with curved text. In inference stage, each pixel at the mountain foot needs to search the path to the mountaintop and this process can be efficiently completed in parallel, yielding the efficiency of our method compared with others. The experiments on MLT, ICDAR2015, RCTW-17 and SCUT-CTW1500 databases demonstrate that the proposed method achieves better or comparable performance in terms of both accuracy and efficiency. It is worth mentioning our method achieves an F-measure of 76.85% on MLT which outperforms the previous methods by a large margin. Code will be made available.

cs.CV↗

arXiv2018

Acoustics-guided evaluation (AGE): a new measure for estimating performance of speech enhancement algorithms for robust ASR

One challenging problem of robust automatic speech recognition (ASR) is how to measure the goodness of a speech enhancement algorithm (SEA) without calculating the word error rate (WER) due to the high costs of manual transcriptions, language modeling and decoding process. Traditional measures like PESQ and STOI for evaluating the speech quality and intelligibility were verified to have relatively low correlations with WER. In this study, a novel acoustics-guided evaluation (AGE) measure is proposed for estimating performance of SEAs for robust ASR. AGE consists of three consecutive steps, namely the low-level representations via the feature extraction, high-level representations via the nonlinear mapping with the acoustic model (AM), and the final AGE calculation between the representations of clean speech and degraded speech. Specifically, state posterior probabilities from neural network based AM are adopted for the high-level representations and the cross-entropy criterion is used to calculate AGE. Experiments demonstrate AGE could yield consistently highest correlations with WER and give the most accurate estimation of ASR performance compared with PESQ, STOI, and acoustic confidence measure using Entropy. Potentially, AGE could be adopted to guide the parameter optimization of deep learning based SEAs to further improve the recognition performance.

eess.AS↗

arXiv2018

DenseRAN for Offline Handwritten Chinese Character Recognition

Recently, great success has been achieved in offline handwritten Chinese character recognition by using deep learning methods. Chinese characters are mainly logographic and consist of basic radicals, however, previous research mostly treated each Chinese character as a whole without explicitly considering its internal two-dimensional structure and radicals. In this study, we propose a novel radical analysis network with densely connected architecture (DenseRAN) to analyze Chinese character radicals and its two-dimensional structures simultaneously. DenseRAN first encodes input image to high-level visual features by employing DenseNet as an encoder. Then a decoder based on recurrent neural networks is employed, aiming at generating captions of Chinese characters by detecting radicals and two-dimensional structures through attention mechanism. The manner of treating a Chinese character as a composition of two-dimensional structures and radicals can reduce the size of vocabulary and enable DenseRAN to possess the capability of recognizing unseen Chinese character classes, only if the corresponding radicals have been seen in training set. Evaluated on ICDAR-2013 competition database, the proposed approach significantly outperforms whole-character modeling approach with a relative character error rate (CER) reduction of 18.54%. Meanwhile, for the case of recognizing 3277 unseen Chinese characters in CASIA-HWDB1.2 database, DenseRAN can achieve a character accuracy of about 41% while the traditional whole-character method has no capability to handle them.

cs.CV↗

arXiv2018

Parsimonious HMMs for Offline Handwritten Chinese Text Recognition

Recently, hidden Markov models (HMMs) have achieved promising results for offline handwritten Chinese text recognition. However, due to the large vocabulary of Chinese characters with each modeled by a uniform and fixed number of hidden states, a high demand of memory and computation is required. In this study, to address this issue, we present parsimonious HMMs via the state tying which can fully utilize the similarities among different Chinese characters. Two-step algorithm with the data-driven question-set is adopted to generate the tied-state pool using the likelihood measure. The proposed parsimonious HMMs with both Gaussian mixture models (GMMs) and deep neural networks (DNNs) as the emission distributions not only lead to a compact model but also improve the recognition accuracy via the data sharing for the tied states and the confusion decreasing among state classes. Tested on ICDAR-2013 competition database, in the best configured case, the new parsimonious DNN-HMM can yield a relative character error rate (CER) reduction of 6.2%, 25% reduction of model size and 60% reduction of decoding time over the conventional DNN-HMM. In the compact setting case of average 1-state HMM, our parsimonious DNN-HMM significantly outperforms the conventional DNN-HMM with a relative CER reduction of 35.5%.

cs.CV↗

arXiv2018

Radical analysis network for zero-shot learning in printed Chinese character recognition

Chinese characters have a huge set of character categories, more than 20,000 and the number is still increasing as more and more novel characters continue being created. However, the enormous characters can be decomposed into a compact set of about 500 fundamental and structural radicals. This paper introduces a novel radical analysis network (RAN) to recognize printed Chinese characters by identifying radicals and analyzing two-dimensional spatial structures among them. The proposed RAN first extracts visual features from input by employing convolutional neural networks as an encoder. Then a decoder based on recurrent neural networks is employed, aiming at generating captions of Chinese characters by detecting radicals and two-dimensional structures through a spatial attention mechanism. The manner of treating a Chinese character as a composition of radicals rather than a single character class largely reduces the size of vocabulary and enables RAN to possess the ability of recognizing unseen Chinese character classes, namely zero-shot learning.

cs.CV↗

arXiv2018

Direct demonstration of the emergent magnetism resulting from the multivalence Mn in a LaMnO3 epitaxial thin film system

Atomically engineered oxide heterostructures provide a fertile ground for creating novel states. For example, a two-dimensional electron gas at the interface between two oxide insulators, giant thermoelectric Seebeck coefficient, emergent ferromagnetism from otherwise nonmagnetic components, and colossal ionic conductivity. Extensive research efforts reveal that oxygen deficiency or lattice strain play an important role in determining these unexpected properties. Herein, by studying the abrupt presence of robust ferromagnetism (up to 1.5 uB/Mn) in LaMnO3-based heterostructures, we find the multivalence states of Mn that play a decisive role in the emergence of ferromagnetism in the otherwise antiferromagnetic LaMnO3 thin films. Combining spatially resolved electron energy-loss spectroscopy, X-ray absorption spectroscopy and X-ray magnetic circular dichroism techniques, we determine unambiguously that the ferromagnetism results from a conventional Mn3+-O-Mn4+ double-exchange mechanism rather than an interfacial effect. In contrast, the magnetic dead layer of 5 unit cell in proximity to the interface is found to be accompanied with the accumulation of Mn2+ induced by electronic reconstruction. These findings provide a hitherto-unexplored multivalence state of Mn on the emergent magnetism in undoped manganite epitaxial thin films, such as LaMnO3 and BiMnO3, and shed new light on all-oxide spintronic devices.

cond-mat.mtrl-sci↗