Statistical Parametric Speech Synthesis Based on Speaker and Language Factorization.
Heiga ZenNorbert BraunschweilerSabine BuchholzMark J. F. GalesKate KnillSacha KrstulovicJavier LatorrePublished in: IEEE Trans. Speech Audio Process. (2012)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- text to speech
- vocal tract
- programming language
- statistical models
- language processing
- language model
- language learning
- kernel density estimators
- speaker identification
- singular value decomposition
- data driven
- multi modal
- matrix factorization
- statistical analysis
- speech signal
- statistical information
- pattern recognition
- speaker recognition
- information retrieval
- computer vision
- speaker diarization
- natural language
- pairwise
- hidden markov models
- dimensionality reduction
- automatic speech recognition
- parametric models