Monaural segregation of voiced speech using discriminative random fields.
Rohit PrabhavalkarZhaozhang JinEric Fosler-LussierPublished in: INTERSPEECH (2009)
Keyphrases
- discriminative random fields
- speech signal
- speech processing
- emotion recognition
- speech recognition
- markov random field
- vocal tract
- automatic speech recognition
- speaker identification
- signal processing
- speech synthesis
- non stationary
- audio visual
- hidden markov models
- recognition engine
- natural language processing
- emotional speech
- speech segments
- linear prediction
- spoken dialogue systems
- human computer interaction
- endpoint detection
- automatic speech recognition systems
- text to speech
- acoustic features
- noisy environments
- speech recognizer
- multi modal
- pairwise