GAN-based Augmentation for Populating Speech Dataset with High Fidelity Synthesized Audio

被引：0

作者：

Back, Moon-Ki ^{[1
]}

Yoon, Seung-Won ^{[1
]}

Lee, Kyu-Chul ^{[1
]}

机构：

[1] Chungnam Natl Univ, Dept Comp Engn, Daejeon, South Korea

来源：

11TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE: DATA, NETWORK, AND AI IN THE AGE OF UNTACT (ICTC 2020) | 2020年

关键词：

Audio augmentation; generative adversarial networks; harmonic percussive separation; progressive growing; speech dataset;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, we present an audio augmentation method that generates synthetic audio using Generative Adversarial Networks (GANs). We propose a training strategy that first uses Harmonic Percussive Source Separation (HPSS) to extract spectral features and then improves the fidelity of the synthesized audio by applying progressively-growing GANs. Our method is demonstrated on a public speech dataset released by Google TensorFlow. When employing our method, the performance evaluated by Frechet Inception Distance (FID) showed 12.514, but 14.012 as for the existing image-generating GANs (lower FID indicates better fidelity).

引用

页码：1267 / 1269

页数：3

共 43 条

[21] GAN-BASED SYNTHETIC MEDICAL IMAGE AUGMENTATION FOR CLASS IMBALANCED DERMOSCOPIC IMAGE ANALYSIS
Alshardan, Amal
Alahmari, Saad
Alghamdi, Mohammed
AL Sadig, Mutasim
Mohamed, Abdullah
Mohammed, Gouse Pasha
FRACTALS-COMPLEX GEOMETRY PATTERNS AND SCALING IN NATURE AND SOCIETY, 2025,
[22] Enhancement of Image Classification Using Transfer Learning and GAN-Based Synthetic Data Augmentation
Chatterjee, Subhajit
Hazra, Debapriya
Byun, Yung-Cheol
Kim, Yong-Woon
MATHEMATICS, 2022, 10 (09)
[23] PlethAugment: GAN-Based PPG Augmentation for Medical Diagnosis in Low-Resource Settings
Kiyasseh, Dani
Tadesse, Girmaw Abebe
Nhan, Le Nguyen Thanh
Van Tan, Le
Thwaites, Louise
Zhu, Tingting
Clifton, David
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2020, 24 (11) : 3226 - 3235
[24] HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
Su, Jiaqi
Jin, Zeyu
Finkelstein, Adam
INTERSPEECH 2020, 2020, : 4506 - 4510
[25] M2H-GAN: A GAN-based Mapping from Machine to Human Transcripts for Speech Understanding
Parcollet, Titouan
Morchid, Mohamed
Bost, Xavier
Linares, Georges
INTERSPEECH 2019, 2019, : 804 - 808
[26] A GAN-Based Data Augmentation Method for Imbalanced Multi-Class Skin Lesion Classification
Su, Qichen
Hamed, Haza Nuzly Abdull
Isa, Mohd Adham
Hao, Xue
Dai, Xin
IEEE ACCESS, 2024, 12 : 16498 - 16513
[27] GAN-Based Data Augmentation for AI-Enabled ATP in Free Space Optical Communication
Liu, Yuchen
Liu, Yejun
Song, Song
Chen, Kun
Guo, Lei
IEEE COMMUNICATIONS LETTERS, 2024, 28 (05) : 1067 - 1071
[28] Additional Look into GAN-based Augmentation for Deep Learning COVID-19 Image Classification
Fedoruk O.
Klimaszewski K.
Ogonowski A.
Kruk M.
Machine Graphics and Vision, 2023, 32 (3-4): : 108 - 124
[29] A GAN-Based Multi-Sensor Data Augmentation Technique for CNC Machine Tool Wear Prediction
Jiang, Yuechi
Drescher, Benny
Yuan, Guoguang
IEEE ACCESS, 2023, 11 : 95782 - 95795
[30] Enhancing Left Ventricular Segmentation in Echocardiograms Through GAN-Based Synthetic Data Augmentation and MultiResUNet Architecture
Kumar, Vikas
Sharma, Nitin Mohan
Mahapatra, Prasant K.
Dogra, Neeti
Maurya, Lalit
Ahmad, Fahad
Dahiya, Neelam
Panda, Prashant
DIAGNOSTICS, 2025, 15 (06)

← 1 2 3 4 5 →