Selective-Tap Blind Dereverberation for Two-Microphone Enhancement of Reverberant Speech.
Kostas KokkinakisPhilipos C. LoizouPublished in: IEEE Signal Process. Lett. (2009)
Keyphrases
- speech signal
- automatic speech recognition
- speech recognition
- sound source
- automatic speech recognition systems
- vocal tract
- noisy environments
- hidden markov models
- linear prediction
- image enhancement
- speaker identification
- speaker diarization
- broadcast news
- image processing
- non stationary
- speaker recognition
- speech quality
- formant frequencies
- audio visual
- fundamental frequency
- visual information
- multi modal
- natural language processing
- speech processing
- speech synthesis
- web pages
- information retrieval
- spontaneous speech
- neural network
- data sets
- real time