Point to the Hidden: Exposing Speech Audio Splicing via Signal Pointer Nets.
Denise MoussaGermans HirschSebastian WankerlChristian RiessPublished in: INTERSPEECH (2023)
Keyphrases
- signal processing
- audio visual
- audio stream
- acoustic signals
- acoustic signal
- speaker identification
- speech processing
- broadcast news
- emotion recognition
- audio signals
- text to speech
- audio signal
- audio features
- noisy environments
- digital audio
- audio video
- speech segments
- automatic transcription
- acoustic features
- speech signal
- visual information
- high frequency
- speech recognition
- cepstral features
- data structure
- speech music discrimination
- multimedia
- prosodic features
- audio recordings
- human language
- non stationary
- multi modal
- visual speech
- frequency domain
- hidden markov models
- speech quality
- speaker recognition
- automatic speech recognition
- splice site
- voice activity detection
- pattern recognition