Large-margin conditional random fields for single-microphone speech separation.
Yu Ting YeungTan LeeCheung-Chi LeungPublished in: INTERSPEECH (2014)
Keyphrases
- conditional random fields
- structured prediction
- structured learning
- graphical models
- hidden markov models
- probabilistic model
- sequence labeling
- random fields
- information extraction
- pairwise
- automatic speech recognition
- image labeling
- generative model
- semi markov
- maximum entropy
- named entity recognition
- markov random field
- higher order
- crf model
- speech recognition
- web page prediction
- sound source
- speaker diarization
- markov networks
- speech signal
- maximum margin
- data mining
- parameter learning
- approximate inference
- undirected graphical models
- hyperplane
- similarity measure
- machine learning