Extracting Efficient Spectrograms From MP3 Compressed Speech Signals for Synthetic Speech Detection.
Ziyue XiangAmit Kumar Singh YadavStefano TubaroPaolo BestaginiEdward J. DelpPublished in: IH&MMSec (2023)
Keyphrases
- speech signal
- speech recognition
- noisy environments
- automatic speech recognition
- vocal tract
- speaker identification
- automatic speech recognition systems
- spectral analysis
- background noise
- hidden markov models
- linear prediction
- non stationary
- blind source separation
- speech enhancement
- machine learning
- language model
- speaker recognition
- acoustic features
- speech quality
- formant frequencies
- speaker verification
- pattern recognition
- mel frequency cepstral coefficients
- image processing
- spectral subtraction
- noisy speech
- neural network