Adaptive beamforming and soft missing data decoding for robust speech recognition in reverberant environments.
Marco KühneRoberto TogneriSven NordholmPublished in: INTERSPEECH (2008)
Keyphrases
- speech recognition
- missing data
- speech signal
- noisy environments
- speech enhancement
- hidden markov models
- missing values
- matrix factorization
- language model
- low rank
- pattern recognition
- speech synthesis
- automatic speech recognition
- speech processing
- sound source
- incomplete data
- speaker identification
- speech recognition technology
- structure from motion
- multiple imputation
- background noise
- speech recognizer
- speech recognition systems
- bayesian networks
- speech recognizers
- denoising
- text classification
- knn
- vocal tract