rastamat

PLP and RASTA (and MFCC, and inversion) in Matlab using melfcc.m and invmelfcc.m. .. Another popular speech feature representation is known as RASTA-PLP, an acronym for Relative Spectral Transform - Perceptual Linear Prediction. PLP was originally proposed by Hynek Hermansky as a way of warping spectra to minimize the differences between speakers while preserving the important speech information [Herm90]. RASTA is a separate technique that applies a band-pass filter to the energy in each frequency subband in order to smooth over short-term noise variations and to remove any constant offset resulting from static spectral coloration in the speech channel e.g. from a telephone line [HermM94]. ..


References in zbMATH (referenced in 27 articles )

Showing results 21 to 27 of 27.
Sorted by year (citations)
  1. Pisarn, C.; Theeramunkong, T.: An HMM-based method for Thai spelling speech recognition (2007)
  2. Saraswathi, S.; Geetha, T. V.: Time scale modification and vocal tract length normalization for improving the performance of tamil speech recognition system implemented using language independent segmentation algorithm (2007) ioport
  3. Kolokolov, A. S.: Correction of the vocal signal distorted by additive noise (2006)
  4. Lu, Lie; Zhang, Hong-Jiang: Unsupervised speaker segmentation and tracking in real-time audio content analysis (2005) ioport
  5. Reynolds, T. Jeff; Antoniou, Christos A.: Experiments in speech recognition using a modular MLP architecture for acoustic modelling. (2003) ioport
  6. Jeong, Jae-Hoon; Kim, Hoon; Kim, Doh-Suk; Lee, Soo-Young: Speaker adaptation based on judge neural networks for real world implementations of voice-command systems (2000)
  7. Kabré, Harouna; Spalanzani, Anne: EVERA: an evolutionary programming environment for adaptive speech processing (2000)