Myeongjin Ko
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Myeongjin Ko has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Yong-Hoon Choi
School of Robotics Kwangwoon University 01897 Seoul South Korea
2 shared publications - Daegyeom Kim
School of Robotics, Kwangwoon University, Seoul, Nowon-gu, South Korea
1 shared publication - Euiyeon Kim
School of Robotics, Kwangwoon University, Seoul, South Korea
1 shared publication Hyungoo Yoon
Department of Electronic Engineering, Myongji College, Seoul, Seodaemun-gu, South Korea
1 shared publicationKyung-Yul Cheon
Electronics and Telecommunications Research Institute (ETRI), Daejeon, Yuseong-gu, South Korea
1 shared publication- Seungkeun Park
ETRI, Daejeon, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 8 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 5, 577-587
Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS
The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to its requirement for many time steps. To address this limitation, recent models such as denoising diffusion implicit models (DDIM) focus on sample generation without explicitly modeling the entire probability distribution, while models like denoising diffusion generative adversarial networks (GAN) combine diffusion processes with GANs. In the field of speech synthesis, a recent diffusion speech synthesis model called DiffGAN-TTS, which utilizes the structure of GANs, has been introduced and demonstrates superior performance in both speech quality and generation speed. In this paper, to further enhance the performance of DiffGAN-TTS, we propose a speech synthesis model with two discriminators: a diffusion discriminator to learn the distribution of the reverse process, and a spectrogram discriminator to learn the distribution of the generated data. Objective metrics such as the structural similarity index measure (SSIM), mel-cepstral distortion (MCD), F0 root mean squared error (F0- RMSE), phoneme error rate (PER), word error rate (WER), as well as subjective metrics like mean opinion score (MOS), are used to evaluate the performance of the proposed model. The evaluation results demonstrate that our model matches or exceeds recent state-of-the-art models like FastSpeech 2 and DiffGAN-TTS across various metrics. Our code and audio samples are available on GitHub.
- 8 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 5, 577-587
Open AccessAdversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS
The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to its requirement for many time steps. To address this limitation, recent models such as denoising diffusion implicit models (DDIM) focus on sample generation without explicitly modeling the entire probability distribution, while models like denoising diffusion generative adversarial networks (GAN) combine diffusion processes with GANs. In the field of speech synthesis, a recent diffusion speech synthesis model called DiffGAN-TTS, which utilizes the structure of GANs, has been introduced and demonstrates superior performance in both speech quality and generation speed. In this paper, to further enhance the performance of DiffGAN-TTS, we propose a speech synthesis model with two discriminators: a diffusion discriminator to learn the distribution of the reverse process, and a spectrogram discriminator to learn the distribution of the generated data. Objective metrics such as the structural similarity index measure (SSIM), mel-cepstral distortion (MCD), F0 root mean squared error (F0- RMSE), phoneme error rate (PER), word error rate (WER), as well as subjective metrics like mean opinion score (MOS), are used to evaluate the performance of the proposed model. The evaluation results demonstrate that our model matches or exceeds recent state-of-the-art models like FastSpeech 2 and DiffGAN-TTS across various metrics. Our code and audio samples are available on GitHub.
- Open Access
- 4 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 15978-15993
Design and Implementation of Traffic Generation Model and Spectrum Requirement Calculator for Private 5G Network
This paper proposes a neural 5G traffic generation model and a methodology for calculating the spectrum requirements of private 5G networks to provide various industrial communication services. To accurately calculate the spectral requirements, it is necessary to analyze the actual data volume and traffic type of industrial cases. However, because there is currently no suitable traffic model to test loads in private 5G networks, we have developed a generative adversarial network (GAN)-based traffic generator that can generate realistic traffic by learning actual traffic traces collected by mobile network operators. In addition, in the case of industrial applications, probability-based traffic models were used in parallel as there were not enough real data to be learned. The proposed 5G traffic generation model is combined with the proposed 5G spectrum calculation methodology, enabling more accurate spectrum requirements calculation through traffic simulation similar to a real-life environment. In this paper, the spectrum requirements are calculated differently according to two types of duplexing, namely frequency division duplexing (FDD) and time division duplexing (TDD). As a guide for companies aiming to provide advanced wireless connectivity for a wide variety of vertical industries using 5G networks, eight use cases defined in the 5G Alliance for Connected Industries and Automation (ACIA) white paper were simulated. The spectrum requirements were calculated under various simulation conditions considering varying traffic loads, deployment scenarios, and duplexing types. Various simulation results confirmed that a bandwidth of at least 22.0 MHz to a maximum of 397.8 MHz is required depending on the deployment scenario.
- 4 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 15978-15993
Open AccessDesign and Implementation of Traffic Generation Model and Spectrum Requirement Calculator for Private 5G Network
This paper proposes a neural 5G traffic generation model and a methodology for calculating the spectrum requirements of private 5G networks to provide various industrial communication services. To accurately calculate the spectral requirements, it is necessary to analyze the actual data volume and traffic type of industrial cases. However, because there is currently no suitable traffic model to test loads in private 5G networks, we have developed a generative adversarial network (GAN)-based traffic generator that can generate realistic traffic by learning actual traffic traces collected by mobile network operators. In addition, in the case of industrial applications, probability-based traffic models were used in parallel as there were not enough real data to be learned. The proposed 5G traffic generation model is combined with the proposed 5G spectrum calculation methodology, enabling more accurate spectrum requirements calculation through traffic simulation similar to a real-life environment. In this paper, the spectrum requirements are calculated differently according to two types of duplexing, namely frequency division duplexing (FDD) and time division duplexing (TDD). As a guide for companies aiming to provide advanced wireless connectivity for a wide variety of vertical industries using 5G networks, eight use cases defined in the 5G Alliance for Connected Industries and Automation (ACIA) white paper were simulated. The spectrum requirements were calculated under various simulation conditions considering varying traffic loads, deployment scenarios, and duplexing types. Various simulation results confirmed that a bandwidth of at least 22.0 MHz to a maximum of 397.8 MHz is required depending on the deployment scenario.