Speech recognition in noisy environments using a switching linear dynamic model for feature enhancement.
Björn W. SchullerMartin WöllmerTobias MoosmayrGerhard RigollPublished in: INTERSPEECH (2008)
Keyphrases
- dynamic model
- speech recognition
- noisy environments
- speech signal
- speaker identification
- hidden markov models
- experimental data
- speaker verification
- cepstral coefficients
- automatic speech recognition
- language model
- pattern recognition
- background noise
- digit recognition
- speech synthesis
- speech enhancement
- speech recognizer
- speech recognition systems
- noisy speech
- voice activity detection
- linear prediction
- word recognition
- image processing
- feature set
- edge detection
- feature vectors