Automatic prosodic prominence detection in speech using acoustic features: an unsupervised system.
Fabio TamburiniPublished in: INTERSPEECH (2003)
Keyphrases
- acoustic features
- speech signal
- speech recognition
- automatic speech recognition
- speaker verification
- prosodic features
- visual features
- noisy environments
- audio features
- music information retrieval
- text to speech synthesis
- cross correlation
- speech synthesis
- mel frequency cepstral coefficients
- text to speech
- audio visual
- audio stream
- speaker identification
- low level
- hidden markov models
- pattern recognition