This paper proposes a technique for speaker and language adaptive training for HMM-based polyglot speech synthesis. Language-specific context-dependencies in the system are captur...
Data sparseness is an ever dominating problem in automatic emotion recognition. Using artificially generated speech for training or adapting models could potentially ease this: t...
SRI International's IraqComm system performs bidirectional speech-to-speech machine translation between English and Iraqi Arabic in the domains of force protection, municipal ...
Michael W. Frandsen, Susanne Riehemann, Kristin Pr...