Structured prediction for speaker identification in TV series.
Elena KnyazevaGuillaume WisniewskiHervé BredinFrançois YvonPublished in: INTERSPEECH (2015)
Keyphrases
- structured prediction
- speaker identification
- speaker recognition
- gaussian mixture model
- speech recognition
- conditional random fields
- noisy environments
- speech signal
- broadcast news
- feature extraction
- graphical models
- noise reduction
- computer vision
- language model
- image classification
- maximum likelihood
- neural network
- hidden markov models
- automatic speech recognition
- feature space