1.9k citations
- Chinese Academy of SciencesCN353 papers
- University of Chinese Academy of SciencesCN228 papers
- Shandong Institute of AutomationCN78 papers
- Beijing Academy of Artificial IntelligenceCN58 papers
- Center for Excellence in Brain Science and Intelligence TechnologyCN57 papers
- Tsinghua UniversityCN26 papers
- Peking UniversityCN16 papers
- National University of SingaporeSG13 papers
- Beijing University of Posts and TelecommunicationsCN12 papers
- Beihang UniversityCN11 papers
- University of Science and Technology of ChinaCN11 papers
- Anhui UniversityCN9 papers
12 papers · 1 filter
Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection
Cunhang Fan, Mingming Ding, Jianhua Tao +4
Most research in synthetic speech detection (SSD) focuses on improving performance on standard noise-free datasets. However, in actual situations, noise interference is usually pre…
Spatial Reconstructed Local Attention Res2Net with F0 Subband for Fake Speech Detection
Cunhang Fan, Jun Xue, Jianhua Tao +4
The rhythm of bonafide speech is often difficult to replicate, which causes that the fundamental frequency (F0) of synthetic speech is significantly different from that of real spe…
Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding
Zengjie Song, Zhaoxiang Zhang
The framework of visually-guided sound source separation generally consists of three parts: visual feature extraction, multimodal feature fusion, and sound signal processing. An on…
An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audio
Xinrui Yan, Jiangyan Yi, Jianhua Tao +5
Many effective attempts have been made for fake audio detection. However, they can only provide detection results but no countermeasures to curb this harm. For many related practic…
Audio Deepfake Detection Based on a Combination of F0 Information and Real Plus Imaginary Spectrogram Features
Jun Xue, Cunhang Fan, Zhao Lv +6
Recently, pioneer research works have proposed a large number of acoustic features (log power spectrogram, linear frequency cepstral coefficients, constant Q cepstral coefficients,…
NeuralDPS: Neural Deterministic Plus Stochastic Model with Multiband Excitation for Noise-Controllable Waveform Generation
Tao Wang, Ruibo Fu, Jiangyan Yi +2
The traditional vocoders have the advantages of high synthesis efficiency, strong interpretability, and speech editability, while the neural vocoders have the advantage of high syn…