研究者詳細 - 中藤　良久

論文 - 中藤　良久

分割表示161 件中 41 - 60 件目／全件表示 >>

Effective speech features for distinguishing mild dementia patients from healthy person 査読有り国際誌

Nishikawa K., Hirakawa R., Kawano H., Nakashi K., Nakatoh Y.

Advances in Intelligent Systems and Computing 1253 AISC 356 - 361 2021年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

The questionnaire method is generally used for present dementia screening. However, this method requires time for 10 to 15 min with a doctor and a clinical psychologist, which puts a burden on hospitals and test subjects. The purpose of this study is to reduce the burden of users by constructing a system to distinguish patients with mild dementia and healthy persons from speech data. Before that this paper examines the effectiveness of speech features. MFCC has been confirmed to be effective in previous research, this paper extracted six kinds of other speech features that are likely to be correlated with symptoms of dementia. This paper got about 90% accuracy rate for a sentence of conversational speech in SVM and Random Forest. Moreover, this paper has calculated the importance of the features by using the SVM-RFE method. As a result, this showed that log-mel spectrum was more important than MFCC.

DOI： 10.1007/978-3-030-55307-4_54

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85089619179&origin=inward

Estimation of Road Damage for Earthquake Evacuation Guidance System Linked with SNS 査読有り国際誌

Yujiro Mihara, Rin Hirakawa, Hideaki Kawano, Kenichi Nakashi, Yoshihisa Nakatoh

Proc. of Congress on Intelligent Systems CIS 2020 2020年09月

Software Log Anomaly Detection Method using HTM Algorithm 査読有り国際誌

Rin Hirakawa, Keitaro Tominaga, Yoshihisa Nakatoh

Proc. of Congress on Intelligent Systems CIS 2020 2020年09月

Study on Software Log Anomaly Detection System with Unsupervised Learning Algorithm 査読有り国際誌

Rin Hirakawa, Keitaro Tominaga, Yoshihisa Nakatoh

Proc. of 2nd International Conference on Human Interaction and Emerging Technologies (IHIET-AI 2020) 2020年08月

Sitting posture discrimination, method for back pain prevention system 査読有り国際誌

Joumori Daiki, Rin Hirakawa, Hideaki Kawano, Kenichi Nakashi, Yoshihisa Nakatoh

Proc. of 2nd International Conference on Human Interaction and Emerging Technologies (IHIET 2020) 2020年08月

Speaker Verification Method Using Hierarchical Temporal Memory for Security System 査読有り国際誌

Yuki Sakaguchi, Rin Hirakawa, Hideaki Kawano, Kenichi Nakashi, Yoshihisa Nakatoh

Proc. of 2nd International Conference on Human Interaction and Emerging Technologies (IHIET 2020) 2020年08月

Blink Detection Using Image Processing to Predict Eye Fatigue 査読有り国際誌

Akihiro Kuwahara, Rin Hirakawa, Hideaki Kawano, Kenichi Nakashi, Yoshihisa Nakatoh

Proc. of 2nd International Conference on Human Interaction and Emerging Technologies (IHIET 2020) 2020年08月

Effective Speech Features for Distinguishing Mild Dementia Patients from Healthy Person 査読有り国際誌

Kazu Nishikawa, Rin Hirakawa, Hideaki Kawano, Kenichi Nakashi, Yoshihisa Nakatoh

Proc. of 2nd International Conference on Human Interaction and Emerging Technologies (IHIET 2020) 2020年08月

Software Log Anomaly Detection Through One Class Clustering of Transformer Encoder Representation 査読有り国際誌

Hirakawa Rin, Tominaga Keitaro, Nakatoh Yoshihisa

Communications in Computer and Information Science ( Springer, Cham ) 1224 ( 1224 ) 655 - 661 2020年07月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

22nd International Conference on Human-Computer Interaction, HCI International 2020, 19-24 July 2020, Copenhagen, Denmark（新型コロナ感染拡大に伴い、現地開催中止）

CiNii Article

CiNii Research

その他リンク： https://ci.nii.ac.jp/naid/120007117049

Electrolarynx system using voice conversion based on WaveRNN 査読有り

Urabe E., Hirakawa R., Kawano H., Nakashi K., Nakatoh Y.

Digest of Technical Papers - IEEE International Conference on Consumer Electronics 2020-January 2020年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2020 IEEE. Voice is very important in our daily life. However, some people cannot speak because of throat surgery. Electrolarynx (EL) is a way for them to speak again but this voice is flat and noisy like a buzzer. Therefore, we propose a new Electrolarynx system based on WaveRNN. When we use it, the EL voice is converted into a voice close to the natural voice. We assume that this system will be provided as a smartphone application. In the experiment, we evaluated the converted voice by the system and found that naturalness improved.

DOI： 10.1109/ICCE46568.2020.9043135

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85082578662&origin=inward

Study on mistype correction support using attention in Japanese input 査読有り

Komatsu R., Hirakawa R., Kawano H., Nakashi K., Nakatoh Y.

Digest of Technical Papers - IEEE International Conference on Consumer Electronics 2020-January 2020年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2020 IEEE. How to input characters without mistakes is one of very important points for the interface, when we consider usability of electronic devices such as personal computers and smartphones. Therefore, in this paper, we examine whether we can classify mistypes for Japanese input and inform the users how they make mistakes using 'Attention' and 'LSTM' of machine learning methods. First, we classified the category of mistypes in Japanese input into seven types (Replacement, Removal, Exchange, Insertion, Involvement, Repetition). Second, we asked subjects to input the displayed words and collected their data. Next, we classified the data and labeled it. Finally, we made the Neural Network (LSTM + Attention) to classify the mistype data and inform how they make mistakes. As a result, the correct answer rate of the Neural Network (LSTM + Attention) was about 70% and we were able to know where point the Neural Network focus on by putting in 'Attention'. We are planning to use 'LSTM' to correct mistype directly and use 'Attention' to inform how they frequently make mistakes in the future.

DOI： 10.1109/ICCE46568.2020.9043138

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85082570013&origin=inward

Study on automatic defect report classification system with self attention visualization 査読有り

Hirakawa R., Tominaga K., Nakatoh Y.

Digest of Technical Papers - IEEE International Conference on Consumer Electronics 2020-January 2020年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2020 IEEE. In recent years, software in devices such as smartphones and tablets has become increasingly multifunctional, and the use of OSS has become essential. In software development using large-scale OSS, it is important to report defects to appropriate personnel promptly. In this paper, we propose a method to classifying defect reports into appropriate categories using fine-tuned BERT and visualize self-attention information. In the evaluation, category classification was performed using defect reports of the actual OSS project. The F1 score was 0.87, which indicated that high-accuracy classification was possible. Also, the visualization results show that category-specific words can be extracted.

DOI： 10.1109/ICCE46568.2020.9043062

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85082612536&origin=inward

Defect Reports Classification with pre-trained BERT 査読有り国際誌

Rin Hirakawa, Keitaro Tominaga, Yoshihisa Nakatoh

Proceedings of ICISIP2019 2019年09月

Study on the classification of road damage during the earthquake using SNS information 査読有り国際誌

Yujiro Mihara, Rin Hirakawa, Hideaki Kawano, Kenichi Nakashi, Yoshihisa Nakatoh

Proceedings of ICISIP2019 2019年09月

Analyze of Acoustic Features to separate Train Announcement 査読有り国際誌

Yuto Kinoshita, Rin Hirakawa, Hideaki Kawano, Kenichi Nakashi, Yoshihisa Nakatoh

Proceedings of ICISIP2019 2019年09月

Analysis of Words Related to Mistypes 査読有り国際誌

Ryuki Komatsu, Rin Hirakawa, Hideaki Kawano, Kenichi Nakashi, Yoshihisa Nakatoh

Proceedings of ICISIP2019 2019年09月

Study on Door-to-door Sales Detection Method in Watching System for Seniors living alone 査読有り

Hirakawa R., Nakatoh Y.

2019 IEEE International Conference on Consumer Electronics, ICCE 2019 2019年03月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2019 IEEE. In recent years, the number of seniors living alone has increased, so the demand for the watching system has increased. In this paper, we propose a method to detect door-to-door sales from voice information with the aim of constructing a watching system to prevent consumer troubles of seniors living alone. In the proposed method, speech recognition is performed on conversation voice acquired from a microphone, and converted into text data. Subsequently, text data is input to the Doc2Vec model that has learned the conversation data on door-to-door sales and the cosine similarity is calculated. In this system, when the similarity exceeds a certain threshold value, it is determined that door-to-door sales is being conducted and a warning is issued to relatives. In order to evaluate the effectiveness of the proposed method, binary classification experiments of conversational text data were conducted. As a result, the area under the ROC curve drawn based on the cosine similarity was 0.94, suggesting that a valid decision was made.

DOI： 10.1109/ICCE.2019.8662118

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85063793011&origin=inward

Study on Mistype Classification in Japanese Input Using Machine Learning 査読有り国際誌

Komatsu R., Nakatoh Y.

2019 IEEE International Conference on Consumer Electronics, ICCE 2019 2019年03月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2019 IEEE. When considering usability of electronic devices such as computers and smartphones, how to input characters without mistakes is a very important point in the interface. Therefore in this paper, we examine classification of mistypes for Japanese input using machine learning. First, we classified the category of mistypes in Japanese input into six types (replacement, removal, exchange, insertion, involvement, repetition). We asked 12 subjects to input the words displayed and saw a trend. Experimental results showed that there was a common trend such as many replacement errors in all subjects, and characteristic mistypes were found for each subject. Next, we made the neural network (RNN • LSTM) to learn the mistype data of all subjects and classified. As a result, the correct answer rate of RNN was 10%, and the correct answer rate of LSTM was 88%. We are planning to use LSTM for correcting mistype in the future.

DOI： 10.1109/ICCE.2019.8661955

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85063782455&origin=inward

Changes in fundamental frequency and gesture of response corresponding to the understanding level of partner's talk 査読有り国際誌

Natsumi K., Saitoh Y., Wakita Y., Nakatoh Y.

Proceedings - 2018 IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2018 83 - 86 2019年02月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2018 IEEE. This study explores a system that estimates the degree of decline in driving ability in elderly people using nonverbal information from daily conversations. To create this system, it is necessary to find factors that are effective for estimating the degree of decline that has reached a problematic level in daily life. In this paper, we consider the case where elderly people cannot understand the partner's talk as their hearing and concentration abilities drop, and we analyze the relation between the degree of understanding of the partner's talk and the nonverbal characteristic of the response utterance. According to the analysis results, both fundamental frequency (F0) values of response utterance and brightness values of the frame difference image for a response scene when a person can understand their partner's talk tend to be higher than that when he/she does not understand the talk. These results indicate that the F0 value of utterances and brightness values of the frame difference images are important factors to estimate the decline in hearing and concentration abilities.

DOI： 10.1109/IICAIET.2018.8638457

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85063133296&origin=inward

Analysis of Mistyping in Hardware Keyboard 査読有り

Ryuki Komatsu, Yoshihisa Nakatoh

Proceedings of ICISIP2018 2018年09月

　前のページ - 次のページ　

<中藤 良久>

論文 - 中藤 良久

<中藤　良久>

論文 - 中藤　良久