国際会議(査読なし)
2024年
■Applying Speaker Retention and Unit-to-Mel Techniques for Enhanced Speaker Consistency in Speech-to-Speech TranslationRui Zhou, Akinori Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
The 21th International Workshop on Emerging ICT 2024/11/9
■A Study on Speaker-Independent Features for Sample-Based Spoken Dialogue System
Takaki Koshikawa, Akinori Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
The 21th International Workshop on Emerging ICT 2024/11/9
■Paper Evaluation of Singing Enthusiasm Using Deep Learning
Jingya Shen, Akinori Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
The 21th International Workshop on Emerging ICT 2024/11/9
2023年
■Evaluation of Environmental Sound Classification using Vision TransformerChanglong Wang, Akinori Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2023/10/31
■Meta Transfer Learning used in Low Resource Speech Recognition
Rui Zhou, Akinori Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2023/10/31
■A preliminary study on photo-realistic facial animation generation using keypoint features
Zikai Shu, Takashi Nose, Akinori Ito
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2023/10/31
■Analysis and Data Augmentation for Conversational Speech Synthesis Based on Dialogue Situation
Shoki Kawanishi, Yuya Chiba, Akinori Ito
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2023/10/31
■A Study on the Effectiveness of Different Recognizers in Low Resource Speech Recognition Using wav2vec2.0
Takaki Koshikawa, Akinori Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2023/10/31
■A Study of a Method for Improving Cartoon Drawing Using Stable Diffusion
Rei Takahashi, Takashi Nose, Akinori Ito
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2023/10/31
2022年
■A Comparison of Key Sentence Estimation Methods for On-Demand Lectures Using Text Summarization Techniques and Prosodic InformationMiki Takeuchi, Akionri Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2022/10/28
■A Comparison of Key Sentence Estimation Methods for On-Demand Lectures Using Text Summarization Techniques and Prosodic Information
Miki Takeuchi, Akionri Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2022/10/28
■A Study on a CALL System for Shadowing Training Using Synchronized Partial Caption
Shuyu Fang, Akinori Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2022/10/28
■Effect of Character Expressions in Low Resource End-to-End Speech Recognition Based on Meta-learning
Rui Zhou, Akinori Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2022/10/28
■Using Curriculum Learning to Optimize the Response of Spoken Dialog System
Xuecheng Niu, Akinori Ito, Takashi Nose
Proceedings of International Workshop on Emerging ICT
International Workshop on Emerging ICT 2022/10/28
2021年
■Simultaneous Generation of Facial Expression and Prosody based on Multimodal Information for Dialogue AgentRyoya Watanabe, Yuya Chiba, Takashi Nose, Akinori Ito
The 18th international Workshop on Emerging ICT 2021/10/29
2020年
■Extraction and Estimation of Sentence Speakability for English Pronunciation EvaluationSatsuki Naijo, Akinori Ito, Takashi Nose
ICT Workshop 2020/11/2
2019年
■Spoken Term Detection Using Japanese Language Posteriorgram for Zero-Resource LanguageSatoru Mizuochi, Yuya Chiba, Takashi Nose, Akinori Ito
ICT Workshop 2019/11/1
■Construction of Multimodal Chat-talk Corpus Considering the Closeness in Dyads and Analysis of Dialog Act
Yoshihiro Yamazaki, Yuya Chiba, Takashi Nose, Akinori Ito
ICT Workshop 2019/11/1
2018年
■Analyzing Effect of Multimodal Information Processing on English ProficiencyHaoran Wu, Yuya Chiba, Takashi Nose, Akinori Ito
ICT Workshop 2018/11/5
2017年
■Improvement of Accent Sandhi Rules Based on Japanese Accent DictionariesHiroto Aoyama, Takashi Nose, Yuya Chiba, Akinori Ito
ICT Workshop 2017/11/2
■Data Collection and Analysis for Automatically Generating Record of Human Behaviors by Environmental Sound Recognition
Takahiro Furuya, Yuya Chiba, Takashi Nose, Akinori Ito
ICT Workshop 2017/11/2
■Changing Impression to the Spoken Dialog System by Gradual Control of Expressions
Yukiko Kageyama, Yuya Chiba, Takashi Nose, Akinori Ito
ICT Workshop 2017/11/2
2016年
■Spectral and pitch modeling with hybrid approach to singing voice synthesis using hidden semi-Markov model and deep neural networkKouki Hongo, Takashi Nose, and Akinori Ito
5th Joint Meeting Acoustical Society of America and Acoustical Society of Japan 2016/11/28
■Improvement of Quality of Voice Conversion Based on Spectral Differential Filter Using STRAIGHT-based Mel-cepstral Coefficients
Harunori Koike, Takashi Nose, Takahiro Shinozaki, Akinori Ito
5th Joint Meeting Acoustical Society of America and Acoustical Society of Japan 2016/11/28
■Detection of singing mistakes from singing voice
Isao Miyagawa, Yuya Chiba,Takashi Nose, Akinori Ito
JCKWorkshop 2016/11/2
■Improvement on Precise Evaluation of Prosody by Human Evaluators Using Prosody Substitution
Hafiyan Prafianto, Takashi Nose and Akinori Ito
RIEC International Symposium on Ultra-Realistic Interactive Acoustic Communications 2016 2016/5/21
■Evaluation of dialogue strategies for non-task-oriented dialogue using MMDAgent
Yukiko Kageyama, Yuya Chiba, Takashi Nose, Akinori Ito
RIEC International Symposium on Ultra-Realistic Interactive Acoustic Communications 2016 2016/5/21
■Speech corpus design for conversational speech synthesizer
Shuhei Yamada, Takashi Nose and Akinori Ito
RIEC International Symposium on Ultra-Realistic Interactive Acoustic Communications 2016 2016/5/21
■The effect of accuracy of DTW on the performance of voice conversion
Harunori Koike, Takashi Nose, Takahiro Shinozaki, Akinori Ito
RIEC International Symposium on Ultra-Realistic Interactive Acoustic Communications 2016 2016/5/21
■A study on the speech rate and intelligibility of Japanese speech for non-native listeners
Jiahe WEI, Takashi NOSE, Akinori ITO
The 10th seminar of A3 foresight program 2016/1/29
■A study on singing voice synthesis based on deep neural networks
Koki Hongo, Takashi Nose, Yuki Saito, Shuhei Yamada, Akinori Ito
The 10th seminar of A3 foresight program 2016/1/29
■Evaluation of selection response for non-task-oriented dialogue using MMDAgent
Yukiko Kageyama, Yuya Chiba, Takashi Nose, Akinori Ito
The 10th seminar of A3 foresight program 2016/1/29
■A study on speaker-independent voice conversion using spectral differential filter based on neural network
Harunori Koike, Takashi Nose, Takahiro Shinozaki, Akinori Ito
The 10th seminar of A3 foresight program 2016/1/29
2015年
■A study on quick model training in HMM-based speech synthesisShuhei Yamada, Takashi Nose, Akinori Ito
International Workshop on IT Convergence systems 2015/11/2
■A study on consistent accent labeling for HMM-based speech synthesis
Ryota Takahashi, Takashi Nose, Akinori Ito
International Workshop on IT Convergence systems 2015/11/2
■Facial image conversion based on transformation of Animation Units using a DNN
Yuki Saito, Takashi Nose, Takahiro Shinozaki, Akinori Ito
A3 Workshop 2015/10/31
■Development of Spoken Dialogue System Generating Emotional Speech Response Based on Utterance State Estimation
Taketo Kase, Takashi Nose, Yuya Chiba, Akinori Ito
A3 Workshop 2015/10/31
■Design and evaluation of phonetically and prosodically balanced emtion-dependent sentence set for emotional speech database
Emika Takeishi, Takashi Nose, Taketo Kase, Akinori Ito
A3 Workshop 2015/10/31
■Singing Error Detection from the Singing Voice based on Dynamic Time Warping
Isao Miyagawa, Takashi Nose, Akinori Ito
A3 Workshop 2015/10/31
■Speaker-Adapted Realtime Talking Avatar on the Internet Using Kinect and Voice Conversion
Yuki Igarashi, Takashi Nose, Yusuke Yamada
A3 Workshop 2015/6/4
■Conversion of Speaker’s Facial Image Using Speech and Animation Unit for Video Chatting
Yuki Saito, Takashi Nose, Takahiro Shinozaki, Akinori Ito
A3 Workshop 2015/6/4
2014年
■Tempo modification of music signal preserving attack-decay structure of sounds using sinusoidal modelTsukasa Nishino, Yuki Igarashi, Takashi Nose, Akinori Ito
WEC 2014 2014/10/27
■Low Complexity Feature Extraction Using Haar-Wavelet Transformation for Embedded Speech Recognition
Kiyoaki Matsui, Yuya Chiba, Takashi Nose, Akinori Ito
WEC 2014 2014/10/27
■Language Modeling for Speech Recognition of Disaster Information
Kenta Shiga, Takashi Nose, Akinori Ito
The 7th seminar of A3 foresight program 2014/5/26
■Singing Style Control for HMM-Based Expressive Singing Voice Synthesis
Takashi Nose
The 7th seminar of A3 foresight program 2014/5/26
2013年
■Paralinguistic feature of command speech towards a mobile robot under the robot's unintended behaviorNoriko Totsuka, Akinori Ito
The 5th seminar of A3 foresight program 2013/10/15
■Subjective evaluation of latency and speech degradation of VoIP speech under severe loss condition
Masahito Okamoto, Takeshi Nagano, Akinori Ito
The 5th seminar of A3 foresight program 2013/10/15
より過去の発表