Search

Your search keyword '"Lee, Yong-Hyeok"' showing total 31 results
Start Over Author "Lee, Yong-Hyeok"
31 results on '"Lee, Yong-Hyeok"'

1. iPhonMatchNet: Zero-Shot User-Defined Keyword Spotting Using Implicit Acoustic Echo Cancellation

Author

Lee, Yong-Hyeok and Cho, Namhyun

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing, Electrical Engineering and Systems Science - Signal Processing
Abstract

In response to the increasing interest in human--machine communication across various domains, this paper introduces a novel approach called iPhonMatchNet, which addresses the challenge of barge-in scenarios, wherein user speech overlaps with device playback audio, thereby creating a self-referencing problem. The proposed model leverages implicit acoustic echo cancellation (iAEC) techniques to increase the efficiency of user-defined keyword spotting models, achieving a remarkable 95% reduction in mean absolute error with a minimal increase in model size (0.13%) compared to the baseline model, PhonMatchNet. We also present an efficient model structure and demonstrate its capability to learn iAEC functionality without requiring a clean signal. The findings of our study indicate that the proposed model achieves competitive performance in real-world deployment conditions of smart devices., Comment: Accepted to ICASSP 2024

Published
2023

2. PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords

Author

Lee, Yong-Hyeok and Cho, Namhyun

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound, Electrical Engineering and Systems Science - Signal Processing
Abstract

This study presents a novel zero-shot user-defined keyword spotting model that utilizes the audio-phoneme relationship of the keyword to improve performance. Unlike the previous approach that estimates at utterance level, we use both utterance and phoneme level information. Our proposed method comprises a two-stream speech encoder architecture, self-attention-based pattern extractor, and phoneme-level detection loss for high performance in various pronunciation environments. Based on experimental results, our proposed model outperforms the baseline model and achieves competitive performance compared with full-shot keyword spotting models. Our proposed model significantly improves the EER and AUC across all datasets, including familiar words, proper nouns, and indistinguishable pronunciations, with an average relative improvement of 67% and 80%, respectively. The implementation code of our proposed model is available at https://github.com/ncsoft/PhonMatchNet.

Published
2023
Full Text
View/download PDF

4. Overcoming label noise in audio event detection using sequential labeling

Author

Kim, Jae-Bin, Mun, Seongkyu, Oh, Myungwoo, Choe, Soyeon, Lee, Yong-Hyeok, and Park, Hyung-Min

Subjects
Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

This paper addresses the noisy label issue in audio event detection (AED) by refining strong labels as sequential labels with inaccurate timestamps removed. In AED, strong labels contain the occurrence of a specific event and its timestamps corresponding to the start and end of the event in an audio clip. The timestamps depend on subjectivity of each annotator, and their label noise is inevitable. Contrary to the strong labels, weak labels indicate only the occurrence of a specific event. They do not have the label noise caused by the timestamps, but the time information is excluded. To fully exploit information from available strong and weak labels, we propose an AED scheme to train with sequential labels in addition to the given strong and weak labels after converting the strong labels into the sequential labels. Using sequential labels consistently improved the performance particularly with the segment-based F-score by focusing on occurrences of events. In the mean-teacher-based approach for semi-supervised learning, including an early step with sequential prediction in addition to supervised learning with sequential labels mitigated label noise and inaccurate prediction of the teacher model and improved the segment-based F-score significantly while maintaining the event-based F-score.

Published
2020

11. Why Cellulose-Based Electrochemical Energy Storage Devices?

Author

Wang, Zhaohui, Lee, Yong-Hyeok, Kim, Sang-Woo, Seo, Ji-Young, Lee, Sang-Young, Nyholm, Leif, Wang, Zhaohui, Lee, Yong-Hyeok, Kim, Sang-Woo, Seo, Ji-Young, Lee, Sang-Young, and Nyholm, Leif

Abstract

Recent findings demonstrate that cellulose, a highly abundant, versatile, sustainable, and inexpensive material, can be used in the preparation of very stable and flexible electrochemical energy storage devices with high energy and power densities by using electrodes with high mass loadings, composed of conducting composites with high surface areas and thin layers of electroactive material, as well as cellulose-based current collectors and functional separators. Close attention should, however, be paid to the properties of the cellulose (e.g., porosity, pore distribution, pore-size distribution, and crystallinity). The manufacturing of cellulose-based electrodes and all-cellulose devices is also well-suited for large-scale production since it can be made using straightforward filtration-based techniques or paper-making approaches, as well as utilizing various printing techniques. Herein, the recent development and possibilities associated with the use of cellulose are discussed, regarding the manufacturing of electrochemical energy storage devices comprising electrodes with high energy and power densities and lightweight current collectors and functional separators.

Published
2021
Full Text
View/download PDF

31. Why Cellulose-Based Electrochemical Energy Storage Devices?

Author

Wang Z, Lee YH, Kim SW, Seo JY, Lee SY, and Nyholm L

Abstract

Recent findings demonstrate that cellulose, a highly abundant, versatile, sustainable, and inexpensive material, can be used in the preparation of very stable and flexible electrochemical energy storage devices with high energy and power densities by using electrodes with high mass loadings, composed of conducting composites with high surface areas and thin layers of electroactive material, as well as cellulose-based current collectors and functional separators. Close attention should, however, be paid to the properties of the cellulose (e.g., porosity, pore distribution, pore-size distribution, and crystallinity). The manufacturing of cellulose-based electrodes and all-cellulose devices is also well-suited for large-scale production since it can be made using straightforward filtration-based techniques or paper-making approaches, as well as utilizing various printing techniques. Herein, the recent development and possibilities associated with the use of cellulose are discussed, regarding the manufacturing of electrochemical energy storage devices comprising electrodes with high energy and power densities and lightweight current collectors and functional separators., (© 2020 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.)

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results