Mask estimation employing Posterior-based Representative Mean for missing-feature speech recognition with time-varying background noise.
Wooil KimJohn H. L. HansenPublished in: ASRU (2009)
Keyphrases
- speech recognition
- background noise
- speech signal
- noisy environments
- noisy speech
- cepstral coefficients
- automatic speech recognition
- language model
- speech recognition technology
- speaker identification
- hidden markov models
- speech processing
- speech recognizer
- speech synthesis
- speech recognition systems
- low contrast
- pattern recognition
- adaptive filtering
- linear prediction
- feature vectors
- vocal tract
- speaker recognition
- feature set
- posterior probability
- probabilistic model
- non stationary
- speaker independent
- spectral subtraction
- image processing