Experiment with GMM-Based Artefact Localization in Czech Synthetic Speech.
Jirí PribilAnna PribilováJindrich MatousekPublished in: TSD (2015)
Keyphrases
- speaker recognition
- speaker identification
- gaussian mixture model
- speech recognition
- voice activity detection
- speech signal
- language independent
- speaker verification
- vector quantization
- gaussian mixture modeling
- mixture model
- broadcast news
- automatic speech recognition
- gaussian mixture
- mel frequency cepstral coefficients
- background subtraction
- em algorithm
- real images are presented
- text to speech
- localization algorithm
- automatically generated
- audio visual
- speech retrieval
- bayesian networks
- recognition engine
- linear predictive
- accurate localization
- real world
- probabilistic neural network
- dialogue system
- expectation maximization
- maximum likelihood
- feature vectors
- feature space
- pattern recognition
- image segmentation