Structurally discriminative graphical models for automatic speech recognition - results from the 2001 Johns Hopkins Summer Workshop.
Geoffrey ZweigJeff A. BilmesThomas RichardsonKarim FilaliKaren LivescuPeng XuKirk JacksonYigal BrandmanEric D. SandnessEva HoltzJerry TorresBill ByrnePublished in: ICASSP (2002)
Keyphrases
- graphical models
- automatic speech recognition
- johns hopkins
- speech recognition
- belief propagation
- probabilistic model
- probabilistic inference
- broadcast news
- conditional random fields
- speech signal
- conversational speech
- random variables
- probabilistic graphical models
- hidden markov models
- word error rate
- approximate inference
- bayesian networks
- structure learning
- speech retrieval
- markov networks
- belief networks
- public health
- map inference
- semi supervised
- conditional independence
- max margin
- factor graphs
- chain graphs
- message passing
- feature extraction
- pattern recognition
- information systems