检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Qian-Bei Hong Chung-Hsien Wu Hsin-Min Wang Chien-Lin Huang Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Tainan Taiwan PingAn AI Lab Palo Alto CA USA

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

This paper aims to improve speaker embedding representation based on x-vector for extracting more detailed information for speaker verification. We propose a statistics pooling time delay neural network (TDNN), in which the TDNN structure integrates statistics pooling for each layer, to consider the variation of temporal context in frame-level transformation. The proposed feature vector, named as statsvector, are compared with the baseline x-vector features on the VoxCeleb dataset and the Speakers in the Wild (SITW) dataset for speaker verification. The experimental results showed that the proposed stats-vector with score fusion achieved the best performance on VoxCeleb1 dataset. Furthermore, considering the interference from other speakers in the recordings, we found that the proposed statsvector efficiently reduced the interference and improved the speaker verification performance on the SITW dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data Selection Based on Phoneme Affinity Matrix for Electrolarynx Speech Recognition

Data Selection Based on Phoneme Affinity Matrix for Electrol...

引用

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

作者： I-Ting Hsieh Chung-Hsien Wu Shu-Wei Tsa Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Tainan Taiwan Dept. of Otolaryngology National Cheng Kung University Hospital Taiwan

Electrolarynx (EL) is a communicative aid for the patient after laryngectomy to generate communicable speech. Since EL speech exhibits low speech intelligibility and produces loud noise, understanding the content of the speech remains challenging for listeners, even if the patient is proficient in using the EL device. Accordingly, it is important to develop the tools that offer additional communication methods. Automatic speech recognition (ASR) of EL speech emerges as a method worth considering in this regard. However, the problem of under-resourced data dramatically degrades the recognition performance of EL speech. Data augmentation is one of the viable solutions for addressing the issue of under-resourced speech data. However, even with an increased health training corpus, the improvement in EL speech recognition may not be satisfactory. Because the characteristics of the EL speech still differ significantly from those of health speech. This paper proposes a data selection method using the phoneme affinity matrix to prioritize the selection of health speech that closely resembles EL speech for data augmentation. The affinity between two phonemes is defined as the similarity of the Phone Posteriorgrams(PPGs) of the two phonemes, considering the phoneme models. The experimental results demonstrate that the approach utilizing data selection based on the phoneme affinity matrix yields superior results compared to both the baseline and the method employing random sampling to select the augmented health speech corpus.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving the Vocabulary Learning by Personalized Proficiency

Improving the Vocabulary Learning by Personalized Proficienc...

引用

IEEE International Conference on Ubi-Media computing

作者： Yi-Zhen Lin Kai-Hsiang Chen Jen-Wei Huang Department of Electrical Engineering National Cheng Kung University Tainan Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan

ISBN: (数字)9781728128207

ISBN: (纸本)9781728128214

To improve the vocabulary ability is very important in language learning. Thus, if we can learn and remember a word very effectively, then we will be able to master a language more quickly. Therefore, many scholars began to propose related research. Due to the learning mechanism of human brain, sometimes when people learn a new knowledge they may forgot at a short time. In order to make the consideration more complete, after analyzing Hermann Ebbinghaus's forgetting curve experiment, we added two variables, one is the acceptance of each word by the same person, and the other is the ability of different people to remember vocabulary. With the above two parameters, we want to design a system to help user to review the vocabulary which may be forgetting before. The forgetting curve can be personalized, and it is more accurate to calculate the best time for each user to review the vocabulary.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LSTM-based Text Emotion Recognition Using Semantic and Emotional Word Vectors

LSTM-based Text Emotion Recognition Using Semantic and Emoti...

引用

Asian Conference on Affective computing and intelligent Interaction (ACII Asia)

作者： Ming-Hsiang Su Chung-Hsien Wu Kun-Yi Huang Qian-Bei Hong Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Tainan Taiwan

ISBN: (纸本)9781538653128

This study proposes a long-short term memory (LSTM)-based approach to text emotion recognition based on semantic word vector and emotional word vector of the input text. For each word in an input text, the semantic word vector is extracted from the word 2vec model. Besides, each lexical word is projected to all the emotional words defined in an affective lexicon to derive an emotional word vector. An autoencoder is then adopted to obtain the bottleneck features from the emotional word vector for dimensionality reduction. The autoencoder bottleneck features are then concatenated with the features in the semantic word vector to form the final textual features for emotion recognition. Finally, given the textual feature sequence of the entire sentence, the LSTM is used for emotion recognition by modeling the contextual emotion evolution of the input text. For evaluation, the NLPCC-MHMC-TE database containing seven emotion categories: anger, boredom, disgust, anxiety, happiness, sadness, and surprise was constructed and used. Five-fold cross-validation was employed to evaluate the performance of the proposed method. Experimental results show that the proposed LSTM-based method achieved a recognition accuracy of 70.66%, improving 5.33% compared with the CNN-based method. Besides, the proposed method based on integration of the semantic word vector and emotional word vector of the input text outperformed that using the individual feature vector.

关键词： Emotion recognition Databases Logic gates Feature extraction Semantics Speech recognition Computer science

来源：评论

学校读者我要写书评

暂无评论

Syncgan: Synchronize the Latent Spaces of Cross-Modal Generative Adversarial Networks

Syncgan: Synchronize the Latent Spaces of Cross-Modal Genera...

引用

IEEE International Conference on multimedia and Expo (ICME)

作者： Wen-Cheng Chen Chien-Wen Chen Min-Chun Hu Dept. of Computer Science and Information Engineering National Cheng Kung University Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan

Generative adversarial network (GAN) has achieved impressive success on cross-domain generation, but it faces difficulty in cross-modal generation due to the lack of a common distribution between heterogeneous data. Most existing methods of conditional based cross-modal GANs adopt the strategy of one-directional transfer and have achieved preliminary success on text-to-image transfer. Instead of learning the transfer between different modalities, we aim to learn a synchronous latent space representing the cross-modal common concept. A novel network component named synchronizer is proposed in this work to judge whether the paired data is synchronous/corresponding or not, which can constrain the latent space of generators in the GANs. Our GAN model, named as SyncGAN, can successfully generate synchronous data (e.g., a pair of image and sound) from identical random noise. For transforming data from one modality to another, we recover the latent code by inverting the mappings of a generator and use it to generate data of different modality. In addition, the proposed model can achieve semi-supervised learning, which makes our model more flexible for practical applications.

关键词： Synchronization Gallium nitride Generators Data models Training Generative adversarial networks Training data

来源：评论

学校读者我要写书评

暂无评论

Exploring Macroscopic Fluctuation of Facial Expression for Mood Disorder Classification

Exploring Macroscopic Fluctuation of Facial Expression for M...

引用

Asian Conference on Affective computing and intelligent Interaction (ACII Asia)

作者： Qian-Bei Hong Chung-Hsien Wu Ming-Hsiang Su Kun-Yi Huang Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Tainan Taiwan Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9781538653128

In clinical diagnosis of mood disorder, a large portion of bipolar disorder patients (BDs) are misdiagnosed as unipolar depression (UDs). Clinicians have confirmed that BDs generally show "reduced affect'' during clinical treatment. Thus, it is expected to build an objective and one-time diagnosis system for diagnosis assistance by using machine-learning techniques. In this study, facial expressions of BD, UD and control group (C) elicited by emotional video clips are collected for exploring temporal fluctuation characteristics of intensities of facial muscles expression among the three groups. The differences of facial expressions among mood disorders are investigated by observing macroscopic fluctuations. To deal with these problems, the corresponding methods for feature extraction and modeling are proposed. From the viewpoint of macroscopic facial expression, action unit (AU) is applied for describing the temporal transformation of muscles. Then, modulation spectrum is used for extracting short-term variation of AU. The multilayer perceptron (MLP)-based disorder prediction model is then applied to obtain the prediction results. For evaluation of the proposed method, 12 subjects for three group are included in the K-fold (K=12) cross validation experiments. The experiment results reached 61.1% classification accuracy, and outperformed the other baseline methods.

关键词： Mood Gold Fluctuations Databases Feature extraction Modulation Predictive models

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition using Convolutional Neural Network with Audio Word-based Embedding

Speech Emotion Recognition using Convolutional Neural Networ...

引用

International Symposium on Chinese Spoken Language Processing

作者： Kun-Yi Huang Chung-Hsien Wu Qian-Bei Hong Ming-Hsiang Su Yuan-Rong Zeng Department of Computer Science and Information Engineering National Cheng Kung University Taiwan PhD Program for Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan

ISBN: (纸本)9781538656280;9781538656273

A complete emotional expression typically contains a complex temporal course in a natural conversation. Related research on utterance-level, segment-level and multi-level processing lacks understanding of the underlying relation of emotional speech. In this work, a convolutional neural network (CNN) with audio word-based embedding is proposed for emotion modeling. In this study, vector quantization is first applied to convert the low level features of each speech frame into audio words using k-means algorithm. Word2vec is adopted to convert an input speech utterance into the corresponding audio word vector sequence. Finally, the audio word vector sequences of the training emotional speech data with emotion annotation are used to construct the CNN- based emotion model. The NCKU-ES database, containing seven emotion categories: happiness, boredom, anger, anxiety, sadness, surprise and disgust, was collected and five-fold cross validation was used to evaluate the performance of the proposed CNN-based method for speech emotion recognition. Experimental results show that the proposed method achieved an emotion recognition accuracy of 82.34%, improving by 8.7% compared to the Long Short Term Memory (LSTM)- based method, which faced the challenging issue of long input sequence. Comparing with raw features, the audio word-based embedding achieved an improvement of 3.4% for speech emotion recognition.

关键词： Emotion recognition Feature extraction Speech recognition Acoustics Training Databases Neural networks

来源：评论

学校读者我要写书评

暂无评论

Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source Separation

Mixing-Specific Data Augmentation Techniques for Improved Bl...

引用

IEEE Workshop on multimedia Signal Processing

作者： Ching-Yu Chiu Wen-Yi Hsiao Yin-Cheng Yeh Yi-Hsuan Yang Alvin Wen-Yu Su Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan Yating Music Team Taiwan AI Labs Taiwan Research Center for IT Innovation Academia Sinica Taiwan National Cheng Kung University Taiwan

ISBN: (数字)9781728193205

ISBN: (纸本)9781728193236

Blind music source separation has been a popular and active subject of research in both the music information retrieval and signal processing communities. To counter the lack of available multi-track data for supervised model training, a data augmentation method that creates artificial mixtures by combining tracks from different songs has been shown useful in recent works. Following this light, we examine further in this paper extended data augmentation methods that consider more sophisticated mixing settings employed in the modern music production routine, the relationship between the tracks to be combined, and factors of silence. As a case study, we consider the separation of violin and piano tracks in a violin piano ensemble, evaluating the performance in terms of common metrics, namely SDR, SIR, and SAR. In addition to examining the effectiveness of these new data augmentation methods, we also study the influence of the amount of training data. Our evaluation shows that the proposed mixing-specific data augmentation methods can help improve the performance of a deep learning-based model for source separation, especially in the case of small training data.

关键词： Training Source separation Training data Production Data models Multiple signal classification Music information retrieval

来源：评论

学校读者我要写书评

暂无评论

Source separation-based data augmentation for improved joint beat and downbeat tracking

arXiv

引用

arXiv 2021年

作者： Chiu, Ching-Yu Ching, Joann Hsiao, Wen-Yi Chen, Yu-Hua Su, Alvin Wen-Yu Yang, Yi-Hsuan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Academia Sinica Taiwan Research Center for IT Innovation Academia Sinica Taiwan Yating Music Team Taiwan AI Labs Taiwan Dept. CSIE National Cheng Kung University

Due to advances in deep learning, the performance of automatic beat and downbeat tracking in musical audio signals has seen great improvement in recent years. In training such deep learning based models, data augmentation has been found an important technique. However, existing data augmentation methods for this task mainly target at balancing the distribution of the training data with respect to their tempo. In this paper, we investigate another approach for data augmentation, to account for the composition of the training data in terms of the percussive and non-percussive sound sources. Specifically, we propose to employ a blind drum separation model to segregate the drum and non-drum sounds from each training audio signal, filtering out training signals that are drumless, and then use the obtained drum and non-drum stems to augment the training data. We report experiments on four completely unseen test sets, validating the effectiveness of the proposed method, and accordingly the importance of drum sound composition in the training data for beat and downbeat tracking. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Mixing-specific data augmentation techniques for improved blind violin/piano source separation

arXiv

引用

arXiv 2020年

作者： Chiu, Ching-Yu Hsiao, Wen-Yi Yeh, Yin-Cheng Yang, Yi-Hsuan Su, Alvin Wen-Yu Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan Yating Music Team Taiwan AI Labs Taiwan Research Center for IT Innovation Academia Sinica Taiwan Dept. CSIE National Cheng Kung University Taiwan

关键词： Mixing

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：