Robust Endpoint Detection for Speech Recognition Based on Discriminative Feature Extraction.
Koichi YamamotoFiras JablounKlaus ReinhardAkinori KawamuraPublished in: ICASSP (1) (2006)
Keyphrases
- speech recognition
- feature extraction
- noisy environments
- endpoint detection
- pattern recognition
- speaker identification
- hidden markov models
- speech synthesis
- language model
- automatic speech recognition
- speech signal
- speech processing
- cepstral coefficients
- speech understanding
- speech recognition technology
- speech recognizer
- feature selection
- image processing
- speaker independent
- image classification
- semi supervised
- keyword spotting
- speech recognition systems
- speech recognition errors
- speech recognizers
- frequency domain
- feature vectors
- speech retrieval
- digital video library
- speaker dependent
- background noise
- n gram
- feature set
- face recognition