CASIA OpenIR

Browse/Search Results:  1-6 of 6 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
SceneFake: An initial dataset and benchmarks for scene fake audio detection 期刊论文
PATTERN RECOGNITION, 2024, 卷号: 152, 页码: 12
Authors:  Yi, Jiangyan;  Wang, Chenglong;  Tao, Jianhua;  Zhang, Chu Yuan;  Fan, Cunhang;  Tian, Zhengkun;  Ma, Haoxin;  Fu, Ruibo
Favorite  |  View/Download:15/0  |  Submit date:2024/07/04
Scene manipulation  Fake audio detection  Speech enhancement  SceneFake dateset  
Emotion selectable end-to-end text-based speech editing 期刊论文
ARTIFICIAL INTELLIGENCE, 2024, 卷号: 329, 页码: 16
Authors:  Wang, Tao;  Yi, Jiangyan;  Fu, Ruibo;  Tao, Jianhua;  Wen, Zhengqi;  Zhang, Chu Yuan
Favorite  |  View/Download:10/0  |  Submit date:2024/07/03
Emotion selectable  Text-based speech editing  Emotion decoupling  Mask prediction  Few-shot learning  Text-to-speech  
Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveforms 会议论文
, Taiyuan, Shanxi, China, 2024-07-27
Authors:  Zhang, Chu Yuan;  Yi, Jiangyan;  Tao, Jianhua;  Wang, Chenglong;  Yan, Xinrui
Adobe PDF(2254Kb)  |  Favorite  |  View/Download:23/12  |  Submit date:2024/06/26
面向生成语音的模型指纹分析研究 学位论文
, 2024
Authors:  ZHANG, CHU YUAN
Adobe PDF(2152Kb)  |  Favorite  |  View/Download:23/0  |  Submit date:2024/06/25
生成语音  语音生成方法辨别  声学模型  声码器  模型指纹分析  
Multi-Scale Permutation Entropy for Audio Deepfake Detection 会议论文
, 韩国首尔, 2024-4-14
Authors:  Chenglong Wang;  He JY(何佳毅);  Jiangyan Yi;  Jianhua Tao;  Chu Yuan Zhang;  Xiaohui Zhang
Adobe PDF(997Kb)  |  Favorite  |  View/Download:49/16  |  Submit date:2024/06/13
Adversarial Multi-Task Learning for Mandarin Prosodic Boundary Prediction With Multi-Modal Embeddings 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2023, 卷号: 31, 页码: 2963-2973
Authors:  Yi, Jiangyan;  Tao, Jianhua;  Fu, Ruibo;  Wang, Tao;  Zhang, Chu Yuan;  Wang, Chenglong
Favorite  |  View/Download:78/0  |  Submit date:2023/11/17
Adversarial training  multi-task learning  prosodic boundaries  speech synthesis  multi-modal embeddings