Showing papers by "Arnon D. Cohen published in 1991"

Acoustic transmission of the respiratory system using speech stimulation

Abstract: Two methods for the analysis of the acoustic transmission of the respiratory system are presented. Continuous speech utterance is used as acoustic stimulation. The transmitted acoustic signal is recorded from various sites over the chest wall. The autoregressive (AR) method analyzes the power spectral density function of the transmitted sound, which depends heavily on the microphone assembly and the utterance. The method was applied to a screening problem and was tested on a small database that consisted of 19 normal and five abnormal patients. Using the first five AR coefficients and the prediction error of an AR(10) model as discriminating features the system screens all abnormals. An autoregressive moving average (ARMA) method that eliminates the dependence on microphone and utterances is proposed. In this method, the generalized least squares identification algorithm is used to estimate the ARMA transfer function of the respiratory system. The normal transfer function demonstrates a peak at the range of 130-250 Hz and sharp decrease in gain for higher frequencies. A pulmonary fibrotic patient demonstrated a peak at the same frequency range, a much higher gain in the high-frequency range, with an additional peak at about 700 Hz. It is concluded that speech-stimulated chest analysis systems have the potential of yielding important clinical information. >

HMM recognition of Hebrew phonemes

Abstract: This paper describes a speaker dependent system comprising two independent stages. The first stage performs segmentation of the speech to phoneme (or sub phoneme) sections while the second stage performs phoneme classification (labeling). Several labeling procedures based on hidden Markov model are described. A simple continuous speech adaptive phoneme segmentation algorithm is introduced. In an experimental evaluation of the system 93.86% correct boundary marks were received by the suggested adaptive phoneme segmentation algorithm. Recognition rate was 72.38% received for phonemes segmented manually and 68.94% for phonemes segmented using the suggested algorithm. These results are comparable with reported phoneme recognition systems in English and other languages. >