Regularized MVDR spectrum estimation-based robust feature extractors for speech recognition.
Md. Jahangir AlamPatrick KennyDouglas D. O'ShaughnessyPublished in: INTERSPEECH (2013)
Keyphrases
- speech recognition
- feature extractors
- noisy environments
- hidden markov models
- language model
- speech signal
- pattern recognition
- speech recognition technology
- automatic speech recognition
- speech recognizer
- speech processing
- speech synthesis
- speech recognition systems
- estimation error
- speaker identification
- feature extractor
- speaker dependent
- feature extraction
- isolated word
- feature set
- similarity measure