Speech enhancement using PCA and variance of the reconstruction error in distributed speech recognition.
Amin Haji AbolhassaniSid-Ahmed SelouaniDouglas D. O'ShaughnessyPublished in: ASRU (2007)
Keyphrases
- speech recognition
- reconstruction error
- speech enhancement
- noisy environments
- speech signal
- noisy speech
- singular value decomposition
- principal component analysis
- hidden markov models
- language model
- automatic speech recognition
- sparse representation
- vocal tract
- speech synthesis
- background noise
- pattern recognition
- linear prediction
- feature extraction
- filter bank
- noise reduction
- signal to noise ratio
- subband
- high dimensional
- face recognition
- dimensionality reduction
- feature space
- similarity measure