检索结果-内蒙古大学图书馆

14th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2013)

作者： Ishii, Takaaki Komiyama, Hiroki Shinozaki, Takahiro Horiuchi, Yasuo Kuroiwa, Shingo Chiba Univ Grad Sch Adv Integrat Sci Div Informat Sci Chiba Japan Tokyo Inst Technol Interdisciplinary Grad Sch Sci & Engn Dept Informat Proc Tokyo Japan

ISBN: (纸本)9781629934433

denoising autoencoder is applied to reverberant speech recognition as a noise robust front-end to reconstruct clean speech spectrum from noisy input. In order to capture context effects of speech sounds, a window of multiple short-windowed spectral frames are concatenated to form a single input vector. Additionally, a combination of short and long-term spectra is investigated to properly handle long impulse response of reverberation while keeping necessary time resolution for speech recognition. Experiments are performed using the CENSREC-4 dataset that is designed as an evaluation framework for distant-talking speech recognition. Experimental results show that the proposed denoising autoencoder based front-end using the short-windowed spectra gives better results than conventional methods. By combining the long-term spectra, further improvement is obtained. The recognition accuracy by the proposed method using the short and long-term spectra is 97.0% for the open condition test set of the dataset, whereas it is 87.8% when a multi condition training based baseline is used. As a supplemental experiment, large vocabulary speech recognition is also performed and the effectiveness of the proposed method has been confirmed.

关键词： denoising autoencoder reverberant speech recognition restricted Boltzmann machine distant-talking speech recognition CENSREC-4

来源：评论

学校读者我要写书评

暂无评论

A denoising autoencoder FOR SPEAKER RECOGNITION. RESULTS ON THE MCE 2018 CHALLENGE 44

A DENOISING AUTOENCODER FOR SPEAKER RECOGNITION. RESULTS ON ...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Font, Roberto Biometr Vox SL Murcia Spain

ISBN: (纸本)9781479981311

We propose a denoising autoencoder ( DAE) for speaker recognition, trained to map each individual ivector to the mean of all ivectors belonging to that particular speaker. The aim of this DAE is to compensate for inter-session variability and increase the discriminative power of the ivectors prior to PLDA scoring. We test the proposed approach on the MCE 2018 1st Multi-target speaker detection and identification Challenge Evaluation. This evaluation presents a call-center fraud detection scenario: given a speech segment, detect if it belongs to any of the speakers in a blacklist. We show that our DAE system consistently outperforms the usual LDA + PLDA pipeline, achieving a Top-S EER of 4.33% and Top-1 EER of 6.11% on the evaluation set, which represents a 45.6% error reduction with respect to the baseline system provided by organizers.

关键词： MCE 2018 challenge speaker recognition blacklist detection denoising autoencoder speaker embeddings

来源：评论

学校读者我要写书评

暂无评论

Music Removal by Convolutional denoising autoencoder in Speech Recognition

Music Removal by Convolutional Denoising Autoencoder in Spee...

引用

Asia-Pacific-Signal-and-Information-Processing-Association Annual Summit and Conference (APSIPA ASC)

作者： Zhao, Mengyuan Wang, Dong Zhang, Zhiyong Zhang, Xuewei Tsinghua Univ Res Inst Informat Technol CSLT Tsinghua Natl Lab Informat Sci & Technol Beijing Peoples R China

ISBN: (纸本)9789881476807

Music embedding often causes significant performance degradation in automatic speech recognition (ASR). This paper proposes a music-removal method based on denoising autoencoder (DAE) that learns and removes music from music-embedded speech signals. Particularly, we focus on convolutional denoising autoencoder (CDAE) that can learn local musical patterns by convolutional feature extraction. Our study shows that the CDAE model can learn patterns of music in different genres and the CDAE-based music removal offers significant performance improvement for ASR. Additionally, we demonstrate that this music-removal approach is largely language independent, which means that a model trained with data in one language can be applied to remove music from speech in another language, and models trained with multilingual data may lead to better performance.

关键词： speech recognition music removal noisy training denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Experience Graph with denoising autoencoder for Zero-Shot Learning in Visual Cognitive Development 27th

Knowledge-Experience Graph with Denoising Autoencoder for Ze...

引用

27th International Conference on Neural Information Processing

作者： Zhang, Xinyue Yang, Xu Liu, Zhiyong Zhang, Lu Ren, Dongchun Fan, Mingyu Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Meituan Dianping Grp Beijing 100190 Peoples R China

ISBN: (纸本)9783030638221;9783030638238

Visual cognitive development is vital for intelligent robots to handle various types of visual tasks rather than predefined ones. It can transfer the classification ability from an original model to a novel task. However, the high reliance on large amounts of data hinders its development. The energy it costs to adjust to the novel tasks is also a tough problem. Thus we propose a model called knowledge-experience graph (KEG) to imitate the mechanisms of human brains. With the help of social knowledge stored in the knowledge graph, the novel classes can be easily added. The combination of the experience via denoising autoencoder (DAE) also takes the relationship in the visual space into account. With the propagation of information among the graph by graph convolutional network (GCN), KEG generates the classifier of the novel tasks effectively. Experiments show that KEG improves the classification accuracy of novel categories on zero-shot learning and accomplishes visual cognitive development to a certain extent.

关键词： GCN Zero-shot learning Cross-task learning Cognitive development Image classification denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Stacked denoising autoencoder Based Stock Market Trend Prediction via K-Nearest Neighbour Data Selection 24th

Stacked Denoising Autoencoder Based Stock Market Trend Predi...

引用

24th International Conference on Neural Information Processing (ICONIP)

作者： Sun, Haonan Rong, Wenge Zhang, Jiayi Liang, Qiubin Xiong, Zhang Beihang Univ Sino French Engineer Sch Beijing Peoples R China Beihang Univ Sch Comp Sci & Engn Beijing Peoples R China

ISBN: (纸本)9783319700960;9783319700953

In financial applications, stock-market trend prediction has long been a popular subject. In this research, we develop a new predictive model to improve the accuracy by enhancing the denoising process which includes a training set selection based on four K-nearest neighbour (KNN) classifiers to generate a more representative training set and a denoising autoencoder-based deep architecture as kernel predictor. Considering the good agreement between closing price trends and daily extreme price movements, we forecast extreme price movements as an indirect channel for realising accurate price-trend prediction. The experimental results demonstrate the effectiveness of the proposed method in terms of its accuracy compared with traditional machine-learning models in four principal Chinese stock indexes and nine leading individual stocks from nine different major industry sectors.

关键词： K-nearest neighbour denoising autoencoder Stock-trend prediction

来源：评论

学校读者我要写书评

暂无评论

TWO-STAGE NOISE AWARE TRAINING USING ASYMMETRIC DEEP denoising autoencoder 41

TWO-STAGE NOISE AWARE TRAINING USING ASYMMETRIC DEEP DENOISI...

引用

41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Lee, Kang Hyun Kang, Shin Jae Kang, Woo Hyun Kim, Nam Soo Seoul Natl Univ Dept Elect & Comp Engn Gwanak POB 34 Seoul 151744 South Korea Seoul Natl Univ INMC Gwanak POB 34 Seoul 151744 South Korea

ISBN: (纸本)9781479999880

Ever since the deep neural network (DNN)-based acoustic model appeared, the recognition performance of automatic speech recognition has been greatly improved. Due to this achievement, various researches on DNN-based technique for noise robustness are also in progress. Among these approaches, the noise-aware training (NAT) technique which aims to improve the inherent robustness of DNN using noise estimates has shown remarkable performance. However, despite the great performance, we cannot be certain whether NAT is an optimal method for sufficiently utilizing the inherent robustness of DNN. In this paper, we propose a novel technique which helps the DNN to address the complex connection between the input and target vectors of NAT smoothly. The proposed method outperformed the conventional NAT in Aurora-5 task.

关键词： Deep neural networks (DNNs) robust speech recognition noise aware training (NAT) denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

denoising autoencoder based Long non-coding RNA-Disease Association Prediction

引用

Procedia Computer Science 2023年 218卷 836-844页

作者： C.P. Gopikrishnan Manu Madhavan

Long non-coding RNAs (lncRNAs) are recent listing in RNA Bioinformatics, which is getting more popular due to their important functional roles. According to the available research, lncRNAs play an essential role in multiple complex diseases. Determining the function of lncRNAs in diseases will help to comprehend many missing links in the disease mechanism. Predicting lncRNAdisease association (LDA) is a crucial stage in this process which is getting at most research interest nowadays. The developments in machine learning and deep learning technologies influenced recent research on LDA models. Most of the methods analyse the interactions of lncRNA with other molecules such as microRNA (miRNA), messenger RNA(mRNA), and proteins. Deep learning models, specifically from autoencoder classes, used extensively in unsupervised learning of features from these associations. This research paper proposes a denoising autoencoder (DAE) based LDA prediction approach. The proposed model uses DAE to learn lncRNA-disease representations from multiple biological networks such as lncRNA-miRNA, miRNA-disease, and disease-lncRNA interactions. The experiments show that the model outperforms other state-of-the-art LDA models concerning the area under the ROC curve (AUC-ROC, 0.94) and the area under precision-recall (AUPR, 0.9592).

关键词： Long non-coding RNA autoencoder denoising autoencoder Representation learning Deep learning Function similarity network

来源：评论

学校读者我要写书评

暂无评论

Ensemble Modeling of denoising autoencoder for Speech Spectrum Restoration 15

Ensemble Modeling of Denoising Autoencoder for Speech Spectr...

引用

15th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2014)

作者： Lu, Xugang Tsao, Yu Matsuda, Shigeki Hori, Chiori Natl Inst Informat & Commun Technol Tokyo Japan Acad Sinica Res Ctr Informat Technol Innovat Taipei Taiwan

ISBN: (纸本)9781634394352

denoising autoencoder (DAE) is effective in restoring clean speech from noisy observations. In addition, it is easy to be stacked to a deep denoising autoencoder (DDAE) architecture to further improve the performance. In most studies, it is supposed that the DAE or DDAE can learn any complex transform functions to approximate the transform relation between noisy and clean speech. However, for large variations of speech patterns and noisy environments, the learned model is lack of focus on local transformations. In this study, we propose an ensemble modeling of DAE to learn both the global and local transform functions. In the ensemble modeling, local transform functions are learned by several DAEs using data sets obtained from unsupervised data clustering and partition. The final transform function used for speech restoration is a combination of all the learned local transform functions. Speech denoising experiments were carried out to examine the performance of the proposed method. Experimental results showed that the proposed ensemble DAE model provided superior restoration accuracy than traditional DAE models.

关键词： denoising autoencoder ensemble modeling speech restoration

来源：评论

学校读者我要写书评

暂无评论

Leveraging Stacked denoising autoencoder in Prediction of Pathogen-Host Protein-Protein Interactions 6

Leveraging Stacked Denoising Autoencoder in Prediction of Pa...

引用

IEEE 6th International Congress on Big Data (BigData Congress)

作者： Chen, Huaming Shen, Jun Wang, Lei Song, Jiangning Univ Wollongong Sch Comp & Informat Technol Wollongong NSW Australia Monash Univ Dept Biochem & Mol Biol Melbourne Vic Australia

ISBN: (纸本)9781538619964

In big data research related to bioinformatics, one of the most critical areas is proteomics. In this paper, we focus on the protein-protein interactions, especially on pathogen-host protein-protein interactions (PHPPIs), which reveals the critical molecular process in biology. Conventionally, biologists apply in-lab methods, including small-scale biochemical, biophysical, genetic experiments and large-scale experiment methods (e.g. yeast-two-hybrid analysis), to identify the interactions. These in-lab methods are time consuming and labor intensive. Since the interactions between proteins from different species play very critical roles for both the infectious diseases and drug design, the motivation behind this study is to provide a basic framework for biologists, which is based on big data analytics and deep learning models. Our work contributes in leveraging unsupervised learning model, in which we focus on stacked denoising autoencoders, to achieve a more efficient prediction performance on PHPPI. In this paper, we further detail the framework based on unsupervised learning model for PHPPI researches, while curating a large imbalanced PHPPI dataset. Our model demonstrates a better result with the unsupervised learning model on PHPPI dataset.

关键词： big data PHPPI denoising autoencoder prediction machine learning

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Series Missing Data Imputation Using Recurrent denoising autoencoder

Multivariate Time Series Missing Data Imputation Using Recur...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhang, Jianye Yin, Peng Chinese Acad Sci Joint Engn Res Ctr Hlth Big Data Intelligent Anal Shenzhen Inst Adv Technol Shenzhen Peoples R China Tsinghua Univ Shenzhen Int Grad Sch Dept Comp Sci & Technol Shenzhen Peoples R China

ISBN: (纸本)9781728118673

This paper presents a novel method for imputing missing data of multivariate time series by adapting the Long Short Term-Memory(LSTM) and denoising autoencoder(DAE). Missing data are ubiquitous in many domains;proper imputation methods can improve performance on many tasks. Our method focus on multivariate time series, applying bidirectional LSTM to learn temporal information and DAE to learn correlation between variables, and we combine these two models by using LSTM as the encoder component of DAE. Several real-world datasets, including electroencephalogram(EEG), electromyogram(EMG) and electronic health records(EHRs), are extracted to test the performance of our method. Through simulation studies, we compare the proposed recurrent denoising autoencoder with several baseline imputation methods and demonstrate its effectiveness in both missing data estimation and label prediction after imputation.

关键词： missing data multivariate time series denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：