PS3DT: Synthetic Speech Detection Using Patched Spectrogram Transformer.
Amit Kumar Singh YadavZiyue XiangKratika BhagtaniPaolo BestaginiStefano TubaroEdward J. DelpPublished in: ICMLA (2023)
Keyphrases
- speech signal
- speech recognition
- automatic speech recognition
- real world
- detection rate
- automatic detection
- fuzzy logic
- object detection
- noisy environments
- pattern analysis
- voice activity detection
- audio visual
- event detection
- detection method
- detection algorithm
- computer vision
- information retrieval
- false alarms
- non stationary
- detection accuracy
- speaker identification
- recognition engine
- wigner distribution