Towards spontaneous speech synthesis - LM based selection of pronunciation variants.
Matthias EichnerSteffen WernerMatthias WolffRüdiger HoffmannPublished in: ICASSP (1) (2003)
Keyphrases
- speech synthesis
- speech recognition
- language model
- language modeling
- hidden markov models
- prosodic features
- pattern recognition
- text to speech
- vocal tract
- speech signal
- automatic speech recognition
- speaker identification
- artificial intelligence
- selection criteria
- real time
- feature selection
- noisy environments
- neural network
- conversational speech
- speaker independent
- spelling correction
- data sets
- selection algorithm
- context sensitive
- information retrieval
- n gram
- query expansion
- information retrieval systems
- computer vision
- evolutionary algorithm
- video sequences