A New Observation Model in the Logarithmic Mel Power Spectral Domain for the Automatic Recognition of Noisy Reverberant Speech.
Volker LeutnantAlexander KruegerReinhold Haeb-UmbachPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2014)
Keyphrases
- automatic recognition
- observation model
- spectral domain
- speech signal
- spectral analysis
- frequency domain
- spatial domain
- particle filter
- speech recognition
- visual tracking
- motion model
- optical coherence tomography
- appearance model
- non stationary
- mrf model
- particle filtering
- markov random field
- three dimensional
- video sequences
- filter responses