A New Pitch Detection Algorithm Based on Wavelet Transform

In this paper, a new event detection pitch detector based on the dyadic wavelet transform was constrcted by selecting an optimal scale. The proposed pitch detector is accurate, robust to noise and computationally simple. Experiments show the superior performance of this event-based pitch detector in comparison with previous event-based pitch detector and classical pitch detectors that use the autocorrelation and the cepsmun methods to estimate the pitch period.

IMAGE-BASED IN VIVO QUANTITATIVE ASSESSMENT OF HUMAN AIRWAY OPENING AND CONTR ACTILITY BY FIBER OPTICAL NA SOPH A RYNGOSCOPY IN HEALTHY AND ASTHMATIC SUBJECTS

Assessment of human airway humen opening is important in diagnosing and understanding the mechanisms of airway dysfunctions such as the excessive airway narrowing in asthma and chronic obstructive pulmonary disease(COPD).Although there are indirect methods to evaluate the airway calibre,direct in vivo measurement of the airway calibre has not been commonly available.With recent advent of the flexible fiber optical nasopharyngoscope with video recording it has become possible to directly visualize the passages of upper and lower airways.However,quan-titative analysis of the recorded video images has been technically challenging.Here,we describe an automatic image processing and analysis method that allows for batch analysis of the images recorded during the endoscopic procedure,thus facilitates image-based quantification of the airway opening.Video images of the airway lumen of volunteer subject were acquired using a fiber optical nasopharyngoscope,and subsequently processed using Gaussian smoothing filter,threshold segment ation,differentiation,and Canny image edge detection,respectively.Thus the area of the open airway lumen was identified and computed using.a predetermined converter of the image scale to true dimension of the imaged object.With this method we measured the opening/narrowing of the glottis during tidal breathing with or without making“Hee"sound or cough.We also used this met hod to measure the opening/narrowing of the primary bronchus of either healthy or asthmatic subjects in response to hist amine and/or albuterol treatment,which also provided an indicator of the airway contractility.Our results demonstrate that the image-based method accurately quantifed the area change waveform of either the glottis or the bronchus as observed by using the optical nasopharygoscope.Importantly,the opening/nar-rowing of the airway lumen generally correlated with the airAow and resistance of the airways,and could differentiate the level of airway contr actility between the healthy and asthmatic subjects.Thus,this quant itative assessment of airway opening may provide a useful tool to ssist clinical diagnosis of airway dysfunctions and understanding the mechanisms of associated pathophysiologies.

Spectrographic Characteristics of Turkish /h/

/h/ is described differently by different researchers. While some argue that /h/ is a glottal fricative, others argue that it is the voiceless counterpart of the following vowel, yet others argue that /h/ is a glide or an approximant. However, de- tailed acoustic studies focusing on /h/ are very limited. This study aims to describe the spectrographic characteristics of /h/ in Turkish. Test words consisted of 48 monosyllabic and disyllabic words containing /h/ which was followed by eight Turkish vowels. Totally 1440 tokens were analyzed. After segmentation, /h/ was classified based on its spectrographic characteristics: 1) segment exhibiting formants, 2) segment exhibiting frication (but no formants) with energy in lower frequencies and 3) segment exhibiting almost no energy. In order to find out if there is a significant difference among these three categories, Chi-square test was applied. The spectrographic characteristics of /h/ in Turkish suggest that it is more like the voiceless version of the surrounding vowels, significantly when it is in syllable initial position and the preceding vowel when in syllable final position.

Estimation method of glottal vocal efficiency based on conversion function of voice source

This investigation was designed to approach a novel estimation method of glottal vocal efficiency (GVE) based on conversion function of voice source. The conversion function of voice source was defined the ratio of supra-glottal acoustic voice source signal to the glottal air volume flow velocity waveform in frequency domain. A carefully designed in vivo canine larynx experiment and several human experiments including different vowels, pressed, falsetto, breath and typical laryngeal diseases were adopted to demonstrate this alternative GVE method. Compared with other vocal efficiency, it is shown that this method could eliminate the contribution from the super vocal tract transmission and resonance to GVE, and reflect the differences of phonation modes. The average magnitude of this conversion function in frequency domain represents GVE, and the variation of the magnitude in fundamental frequency is identical to AC/DC value.

Research on hoarse speech based on vocal cord model and glottal waveform

Considering the fact that hoarse speech is usually caused by pathological changes of vocal cords, and its motion state is reflected by glottal waveform, we present a new method of research on hoarse speech based on dissymmetric four-mass model of vocal cords and glottal wave analysis-synthesis ill this paper. By linking hoarse speech waveform with glottal wave and the vocal cord model, the characteristic parameters of normal speech and hoarse speech before and after laryngeal operation are studied. The parameters of glottal wave periodicity and vocal cord symmetry of hoarse speech are compared with those of normal speech. It is applied to analyzing the relations between model parameters and hoarse mechanism in pathology and physiology. Experimental results show that this new method can unveil the relations between acoustic features and pathological causes of hoarse speech, providing theoretical and experimental bases both for diagnosing laryngeal diseases non-contactly and for improving the tone quality of hoarse speech.

Fundamental frequency patterns of Chinesein different speech modes

The fundamental frequency F0 patterns of standard Chinese were examined at both macro (passage) level and micro (period) level in different speech modes using a Laryngograph. The results show that: 1. The more speech effort the speakcr makes the higher are the mean F0, mid F0, and modal F0,in connected speech, and at the samc time the pitch range is expanded; 2. The values of mean F0, mid F0, and modal F0, are different in different speech styles (isolated syllables, isolatcd sentences, and connected speech); 3. The speech rate has apparent influence on golttal waves but no significant innuence on the F0 distribution function; and 4. The closed phase is roughly inverse of F0 in isolated syllables with tones.