Feature extraction from time-frequency matrices for robust speech recognition.
José C. SeguraM. Carmen BenítezÁngel de la TorreAntonio J. RubioPublished in: INTERSPEECH (2001)
Keyphrases
- speech recognition
- feature extraction
- noisy environments
- speaker identification
- cepstral coefficients
- hidden markov models
- pattern recognition
- speech signal
- automatic speech recognition
- speech processing
- speech synthesis
- wavelet transform
- language model
- speech recognizer
- speech recognition technology
- frequency domain
- speech understanding
- signal processing
- keyword spotting
- principal component analysis
- face recognition
- speaker independent
- speech retrieval
- feature space
- speaker diarization
- speech recognition systems
- computer vision
- image classification
- feature set
- multiresolution
- mobile devices
- image processing
- feature selection