Speech recognition in a home environment using parallel decoding with GMM-based noise modeling.
Kohei MachidaTakashi NoseAkinori ItoPublished in: APSIPA (2014)
Keyphrases
- speech recognition
- home environment
- speaker identification
- noisy environments
- hidden markov models
- speaker recognition
- language model
- speech synthesis
- speech signal
- voice activity detection
- pattern recognition
- speech recognizer
- gaussian mixture model
- automatic speech recognition
- speech processing
- noisy speech
- ambient assisted living
- speech recognition technology
- speech recognition systems
- background noise
- speaker independent
- feature vectors
- feature extraction
- smart home
- signal to noise ratio
- cepstral coefficients
- information retrieval
- face recognition
- bayesian networks
- speaker verification
- management system