Text-to-visual speech synthesis based on parameter generation from HMM.
Takashi MasukoTakao KobayashiMasatsune TamuraJun MasubuchiKeiichi TokudaPublished in: ICASSP (1998)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- hidden markov models
- text generation
- vocal tract
- prosodic features
- visual information
- language model
- video search
- visual features
- keywords
- computer vision
- visual speech
- text mining
- speech corpus
- information retrieval
- database
- speech signal
- key concepts
- text retrieval
- pattern recognition
- free text
- semantic content
- handwritten word recognition
- handwritten words
- natural language generation
- visual cues
- fairy tales
- speaker identification
- handwriting recognition
- news video
- noisy environments
- generation process
- web images
- parameter values
- web documents
- bayesian networks
- machine learning
- neural network