Post-processing of the recognized speech for web presentation of large audio archive.
Marek BohacKarel BlavkaMichaela KucharováSvatava SkodováPublished in: TSP (2012)
Keyphrases
- post processing
- multimedia
- audio visual
- preprocessing
- audio stream
- broadcast news
- text to speech
- audio signals
- speech recognition
- website
- pattern extraction
- metadata
- filtering method
- digital audio
- web content
- shape error concealment
- speaker identification
- web pages
- cepstral features
- speech music discrimination
- web users
- web data
- feature extraction
- multimedia information
- speech signal
- human experts
- audio recordings
- projections onto convex sets
- domain specific
- media streams
- automatic transcription
- domain knowledge
- databases