Automatic Reliability Estimation for Speech Audio Surveillance Recordings.
Clara BorrelliPaolo BestaginiFabio AntonacciAugusto SartiStefano TubaroPublished in: WIFS (2019)
Keyphrases
- audio visual
- speech music discrimination
- audio recordings
- spontaneous speech
- multi modal
- acoustic features
- multimedia
- emotion recognition
- audio stream
- visual information
- audio features
- automatic transcription
- multi stream
- audio signals
- speaker identification
- broadcast news
- gaussian mixture model
- spoken language
- video surveillance
- speech corpus
- speech processing
- music information retrieval
- pattern recognition
- cepstral features
- speech recognition
- visual data
- digital video
- speech synthesis
- audio video
- semi automatic
- prosodic features
- acoustic signals
- text to speech
- feature vectors
- voice activity detection
- speaker verification
- automatic speech recognition