An Automatic Prosody Recognizer using a Coupled Multi-Stream Acoustic Model and a Syntactic-Prosodic Language Model.
Sankaranarayanan AnanthakrishnanShrikanth S. NarayananPublished in: ICASSP (1) (2005)
Keyphrases
- language model
- multi stream
- speech recognition
- hidden markov models
- language modeling
- audio visual speech recognition
- speech synthesis
- audio visual
- document retrieval
- n gram
- probabilistic model
- context sensitive
- information retrieval
- query expansion
- speech signal
- test collection
- automatic speech recognition
- handwriting recognition
- retrieval model
- mixture model
- prosodic features
- dependency structure
- smoothing methods
- ad hoc information retrieval
- query terms
- relevance model
- translation model
- co occurrence
- text to speech