Semi-Automatic Acoustic Model Generation from Large Unsynchronized Audio and Text Chunks.
Michele AlessandriniGiorgio BiagettiAlessandro CurziClaudio TurchettiPublished in: INTERSPEECH (2011)
Keyphrases
- semi automatic
- semi automatically
- text graphics
- fully automatic
- gold standard
- text to speech
- audio signal
- acoustic features
- multimedia
- prosodic features
- keywords
- labor intensive
- domain ontology
- manual annotation
- information retrieval
- web documents
- text mining
- ontology mapping
- audio content
- design rationale
- wrapper generation
- audio visual
- machine learning
- semantic information
- ontology development
- fully automated
- semantic annotation
- information retrieval systems
- landmark extraction