Cross-variety speaker transformation in HSMM-based speech synthesis.
Markus TomanMichael PucherDietmar SchabusPublished in: SSW (2013)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- speaker adaptation
- automatic speech recognition
- speech corpus
- speech signal
- speaker verification
- language model
- wide variety
- hidden markov models
- pattern recognition
- linear transformation
- speaker identification
- wide range
- social networks
- multi modal
- data sets
- image processing
- speaker dependent
- information retrieval