Mixed environment compensation based on maximum a posteriori estimation for robust speech recognition.
Haifeng ShenGang LiuJun GuoPublished in: Artif. Intell. Rev. (2009)
Keyphrases
- speech recognition
- noisy environments
- maximum a posteriori estimation
- hidden markov models
- speech recognizer
- automatic speech recognition
- speech processing
- pattern recognition
- language model
- speech synthesis
- speech signal
- speech understanding
- speaker independent
- keyword spotting
- speaker identification
- speech recognition technology
- speech recognition systems
- gaussian distribution
- speaker dependent
- digit recognition
- background noise
- machine learning
- word recognition
- noise reduction
- image processing