Looking for hidden speech archives in Italian institutions.
Vincenzo GalatàSilvia CalamaiPublished in: CLARIN Annual Conference (2018)
Keyphrases
- speech recognition
- speech signal
- multimedia
- audio visual
- speech synthesis
- metadata
- digital libraries
- endpoint detection
- cultural heritage
- speech recognizer
- educational institutions
- speaker identification
- text to speech synthesis
- speech processing
- speaker recognition
- hidden information
- automatic speech recognition
- text to speech
- spoken language
- multimodal interfaces
- human computer interaction
- lexical features
- legal texts
- recognition engine
- audio stream
- hidden markov models
- document archives
- data sets