• Publications
  • Influence
Perceptual linear predictive (PLP) analysis of speech.
  • H. Hermansky
  • Physics
    The Journal of the Acoustical Society of America
  • 1 April 1990
A new technique for the analysis of speech, the perceptual linear predictive (PLP) technique, which uses three concepts from the psychophysics of hearing to derive an estimate of the auditory spectrum, and yields a low-dimensional representation of speech.
RASTA processing of speech
The theoretical and experimental foundations of the RASTA method are reviewed, the relationship with human auditory perception is discussed, the original method is extended to combinations of additive noise and convolutional noise, and an application is shown to speech enhancement.
Tandem connectionist feature extraction for conventional HMM systems
A large improvement in word recognition performance is shown by combining neural-net discriminative feature processing with Gaussian-mixture distribution modeling.
RASTA-PLP speech analysis technique
The authors have developed a technique that is more robust to such steady-state spectral factors in speech that is conceptually simple and computationally efficient.
TRAPS - classifiers of temporal patterns
The work proposes a radically di erent set of features for ASR where TempoRAl Patterns of spectral energies are used in place of the conventional spectral patterns. The approach has several inherent
Towards ASR on partially corrupted speech
A new highly parallel approach to automatic recognition of speech, inspired by early Fetcher's research on articulation index, and based on independent probability estimates in several sub-bands of
Sub-band based recognition of noisy speech
A new approach to automatic speech recognition based on independent class-conditional probability estimates in several frequency sub-bands is presented. The approach is shown to be especially
Temporal patterns (TRAPs) in ASR of noisy speech
The proposed neural TRAPs are found to yield significant amount of complementary information to that of the conventional spectral feature based ASR system, which results in improved robustness to several types of additive and convolutive environmental degradations.
Should recognizers have ears?