A comparison of LPC and FFT-based acoustic features for noise robust ASR.
Febe de WetBert CranenJohan de VethLou BovesPublished in: INTERSPEECH (2001)
Keyphrases
- noisy environments
- speech signal
- acoustic features
- automatic speech recognition
- speech recognition
- speaker verification
- linear predictive
- spectral analysis
- noise reduction
- speaker identification
- speaker recognition
- hidden markov models
- non stationary
- sound source
- broadcast news
- pattern recognition
- noisy images
- frequency domain
- multi modal
- image classification