Robust Feature Extraction for Speech Recognition by Enhancing Auditory Spectrum.
Md. Jahangir AlamPatrick KennyDouglas D. O'ShaughnessyPublished in: INTERSPEECH (2012)
Keyphrases
- speech recognition
- feature extraction
- noisy environments
- hidden markov models
- pattern recognition
- speaker identification
- cepstral coefficients
- speech signal
- speech recognizer
- speech synthesis
- automatic speech recognition
- speech processing
- language model
- speech recognition technology
- speech recognition systems
- speech recognizers
- speech understanding
- speaker dependent
- signal processing
- principal component analysis
- feature vectors
- speaker independent
- multi modal
- image processing
- speaker diarization
- speech retrieval
- students with learning disabilities
- isolated word
- machine learning
- keyword spotting
- digit recognition
- speaker recognition
- noise reduction
- visual information
- frequency domain
- wavelet transform
- feature selection