• Title/Summary/Keyword: Generative adversarial network (GAN)

Search Result 176, Processing Time 0.023 seconds

Context-Sensitive Spelling Error Correction Techniques in Korean Documents using Generative Adversarial Network (생성적 적대 신경망(GAN)을 이용한 한국어 문서에서의 문맥의존 철자오류 교정)

  • Lee, Jung-Hun;Kwon, Hyuk-Chul
    • Journal of Korea Multimedia Society
    • /
    • v.24 no.10
    • /
    • pp.1391-1402
    • /
    • 2021
  • This paper focuses use context-sensitive spelling error correction using generative adversarial network. Generative adversarial network[1] are attracting attention as they solve data generation problems that have been a challenge in the field of deep learning. In this paper, sentences are generated using word embedding information and reflected in word distribution representation. We experiment with DCGAN[2] used for the stability of learning in the existing image processing and D2GAN[3] with double discriminator. In this paper, we experimented with how the composition of generative adversarial networks and the change of learning corpus influence the context-sensitive spelling error correction In the experiment, we correction the generated word embedding information and compare the performance with the actual word embedding information.

Many-to-many voice conversion experiments using a Korean speech corpus (다수 화자 한국어 음성 변환 실험)

  • Yook, Dongsuk;Seo, HyungJin;Ko, Bonggu;Yoo, In-Chul
    • The Journal of the Acoustical Society of Korea
    • /
    • v.41 no.3
    • /
    • pp.351-358
    • /
    • 2022
  • Recently, Generative Adversarial Networks (GAN) and Variational AutoEncoders (VAE) have been applied to voice conversion that can make use of non-parallel training data. Especially, Conditional Cycle-Consistent Generative Adversarial Networks (CC-GAN) and Cycle-Consistent Variational AutoEncoders (CycleVAE) show promising results in many-to-many voice conversion among multiple speakers. However, the number of speakers has been relatively small in the conventional voice conversion studies using the CC-GANs and the CycleVAEs. In this paper, we extend the number of speakers to 100, and analyze the performances of the many-to-many voice conversion methods experimentally. It has been found through the experiments that the CC-GAN shows 4.5 % less Mel-Cepstral Distortion (MCD) for a small number of speakers, whereas the CycleVAE shows 12.7 % less MCD in a limited training time for a large number of speakers.

Depth Image Restoration Using Generative Adversarial Network (Generative Adversarial Network를 이용한 손실된 깊이 영상 복원)

  • Nah, John Junyeop;Sim, Chang Hun;Park, In Kyu
    • Journal of Broadcast Engineering
    • /
    • v.23 no.5
    • /
    • pp.614-621
    • /
    • 2018
  • This paper proposes a method of restoring corrupted depth image captured by depth camera through unsupervised learning using generative adversarial network (GAN). The proposed method generates restored face depth images using 3D morphable model convolutional neural network (3DMM CNN) with large-scale CelebFaces Attribute (CelebA) and FaceWarehouse dataset for training deep convolutional generative adversarial network (DCGAN). The generator and discriminator equip with Wasserstein distance for loss function by utilizing minimax game. Then the DCGAN restore the loss of captured facial depth images by performing another learning procedure using trained generator and new loss function.

Counterfactual image generation by disentangling data attributes with deep generative models

  • Jieon Lim;Weonyoung Joo
    • Communications for Statistical Applications and Methods
    • /
    • v.30 no.6
    • /
    • pp.589-603
    • /
    • 2023
  • Deep generative models target to infer the underlying true data distribution, and it leads to a huge success in generating fake-but-realistic data. Regarding such a perspective, the data attributes can be a crucial factor in the data generation process since non-existent counterfactual samples can be generated by altering certain factors. For example, we can generate new portrait images by flipping the gender attribute or altering the hair color attributes. This paper proposes counterfactual disentangled variational autoencoder generative adversarial networks (CDVAE-GAN), specialized for data attribute level counterfactual data generation. The structure of the proposed CDVAE-GAN consists of variational autoencoders and generative adversarial networks. Specifically, we adopt a Gaussian variational autoencoder to extract low-dimensional disentangled data features and auxiliary Bernoulli latent variables to model the data attributes separately. Also, we utilize a generative adversarial network to generate data with high fidelity. By enjoying the benefits of the variational autoencoder with the additional Bernoulli latent variables and the generative adversarial network, the proposed CDVAE-GAN can control the data attributes, and it enables producing counterfactual data. Our experimental result on the CelebA dataset qualitatively shows that the generated samples from CDVAE-GAN are realistic. Also, the quantitative results support that the proposed model can produce data that can deceive other machine learning classifiers with the altered data attributes.

Deep Learning-based Single Image Generative Adversarial Network: Performance Comparison and Trends (딥러닝 기반 단일 이미지 생성적 적대 신경망 기법 비교 분석)

  • Jeong, Seong-Hun;Kong, Kyeongbo
    • Journal of Broadcast Engineering
    • /
    • v.27 no.3
    • /
    • pp.437-450
    • /
    • 2022
  • Generative adversarial networks(GANs) have demonstrated remarkable success in image synthesis. However, since GANs show instability in the training stage on large datasets, it is difficult to apply to various application fields. A single image GAN is a field that generates various images by learning the internal distribution of a single image. In this paper, we investigate five Single Image GAN: SinGAN, ConSinGAN, InGAN, DeepSIM, and One-Shot GAN. We compare the performance of each model and analyze the pros and cons of a single image GAN.

An Edge Detection Technique for Performance Improvement of eGAN (eGAN 모델의 성능개선을 위한 에지 검출 기법)

  • Lee, Cho Youn;Park, Ji Su;Shon, Jin Gon
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.10 no.3
    • /
    • pp.109-114
    • /
    • 2021
  • GAN(Generative Adversarial Network) is an image generation model, which is composed of a generator network and a discriminator network, and generates an image similar to a real image. Since the image generated by the GAN should be similar to the actual image, a loss function is used to minimize the loss error of the generated image. However, there is a problem that the loss function of GAN degrades the quality of the image by making the learning to generate the image unstable. To solve this problem, this paper analyzes GAN-related studies and proposes an edge GAN(eGAN) using edge detection. As a result of the experiment, the eGAN model has improved performance over the existing GAN model.

Applications of Generative Adversarial Networks (Generative Adversarial Networks의 응용 현황)

  • Kim, Dong-Wook;Kim, Sesong;Jung, Seung-Won
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2017.11a
    • /
    • pp.807-809
    • /
    • 2017
  • Generative adversarial networks (GAN)에 대한 간략하게 설명하고, MNIST (숫자 손 글씨 데이터 셋)를 이용한 간단한 실험을 통해 GAN 구조 구조의 이해를 돕는다. 그리고 GAN이 어떻게 응용이 되고있는지 다양한 논문들을 통해 살펴본다. 본 고에서는 GAN 논문들을 크게 이미지 스타일 변경, 3D 오브젝트 추정, 손상된 이미지 복원, 언어의 시각화, 기타 등으로 분류하였다.

Morpho-GAN: Unsupervised Learning of Data with High Morphology using Generative Adversarial Networks (Morpho-GAN: Generative Adversarial Networks를 사용하여 높은 형태론 데이터에 대한 비지도학습)

  • Abduazimov, Azamat;Jo, GeunSik
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2020.01a
    • /
    • pp.11-14
    • /
    • 2020
  • The importance of data in the development of deep learning is very high. Data with high morphological features are usually utilized in the domains where careful lens calibrations are needed by a human to capture those data. Synthesis of high morphological data for that domain can be a great asset to improve the classification accuracy of systems in the field. Unsupervised learning can be employed for this task. Generating photo-realistic objects of interest has been massively studied after Generative Adversarial Network (GAN) was introduced. In this paper, we propose Morpho-GAN, a method that unifies several GAN techniques to generate quality data of high morphology. Our method introduces a new suitable training objective in the discriminator of GAN to synthesize images that follow the distribution of the original dataset. The results demonstrate that the proposed method can generate plausible data as good as other modern baseline models while taking a less complex during training.

  • PDF

Improved CycleGAN for underwater ship engine audio translation (수중 선박엔진 음향 변환을 위한 향상된 CycleGAN 알고리즘)

  • Ashraf, Hina;Jeong, Yoon-Sang;Lee, Chong Hyun
    • The Journal of the Acoustical Society of Korea
    • /
    • v.39 no.4
    • /
    • pp.292-302
    • /
    • 2020
  • Machine learning algorithms have made immense contributions in various fields including sonar and radar applications. Recently developed Cycle-Consistency Generative Adversarial Network (CycleGAN), a variant of GAN has been successfully used for unpaired image-to-image translation. We present a modified CycleGAN for translation of underwater ship engine sounds with high perceptual quality. The proposed network is composed of an improved generator model trained to translate underwater audio from one vessel type to other, an improved discriminator to identify the data as real or fake and a modified cycle-consistency loss function. The quantitative and qualitative analysis of the proposed CycleGAN are performed on publicly available underwater dataset ShipsEar by evaluating and comparing Mel-cepstral distortion, pitch contour matching, nearest neighbor comparison and mean opinion score with existing algorithms. The analysis results of the proposed network demonstrate the effectiveness of the proposed network.

Music Generation using Generative Adversarial Network (GAN 알고리즘을 이용한 음악 생성)

  • Im, Hong-Gab;Lee, Sung-Yoen;Shim, Jae-Heon;Lee, Se-Hoon
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2018.07a
    • /
    • pp.397-398
    • /
    • 2018
  • 본 논문에서는 음악 전공자가 아니어도 원하는 악기를 선택하여 손쉽게 자신의 음악을 만들 수 있는 GAN(Generative Adversarial Network) 알고리즘 기반 음악생성 프로그램을 개발하였다. 음악분야는 진입장벽이 높아 음악 전공자가 아니면 자신만의 음악을 제작하기 힘들다. 행사나 소소한 이벤트에서도 쓸 수 있는 자신만의 음악, 방송이나 1인 미디어 등에서도 저작권 걱정 없이 쓸 수 있는 자신만의 음악을 이 GAN 알고리즘 기반 음악생성 프로그램을 이용하여 비전공자라도 손쉽게 음악을 만들 수 있다.

  • PDF