Enhanced Feature Extraction for Speech Detection in Media Audio.
Inseon JangChunghyun AhnJeongil SeoYounseon JangPublished in: INTERSPEECH (2017)
Keyphrases
- feature extraction
- multimedia
- cepstral features
- speaker identification
- audio video
- audio visual
- voice activity detection
- audio stream
- broadcast news
- audio signals
- text to speech
- speech recognition
- audio features
- speech processing
- detection algorithm
- multimedia data
- detection method
- noisy environments
- multimedia information
- feature extraction and classification
- frequency domain
- digital audio
- object detection
- multimedia processing
- preprocessing
- principal component analysis
- signal processing
- multi modal
- iris recognition
- feature selection
- linear predictive
- mel frequency cepstral coefficients
- frequency analysis
- visual information
- multimedia content
- speech signal
- digital video
- face detection
- content based video retrieval
- visual speech
- multi stream
- cepstral coefficients
- visual data
- automatic transcription
- audio visual content
- pattern recognition