Effects of voice therapy on the voice range profiles of dysphonic patients

In a group of chronically dysphonic patients, a voice range profile, or phonetogram, was recorded before and after receiving voice therapy and again 3 months later. The voice range profiles took a wide variety of shapes. Therefore, only measures that did not depend on a smooth contour could be used to describe changes before and after therapy. The main effect of voice therapy was an enlargement on the side of low frequency and low intensity.     

Existence problem of optical correlation based pattern recognition

The existence problem of optical correlation based pattern recognition, namely its range of validity and its limitation, is discussed in this paper conjointly with the function approximation theory of neural networks. The conclusion is that only if the sets to be recognized are linearly separable (which is rare) or the subsets, in which a segmental sample of the targets is involved, are linearly separable, can the classical 4f optical correlation system carry out the task of recognition inerrably. The recognition principle of a joint transform correlator is the same as that of a 4f system, and so is its range of validities. Based on the demonstration of the existence problem of optical correlation based pattern recognition an evaluation on some important problems that were studied in this field over the past 40 years is presented explicitly.     

闪电光电信号的同步观测与闪电类型模式识别

 利用宽带电场仪和光学纹波探头,对2006年夏季广东省从化地区发生的自然闪电的光电信号进行了同步观测,并对结果进行了统计分析。统计结果表明：闪电光信号脉冲的发生时间和峰值到达时间总是滞后于电信号,并且脉冲上升沿和宽度也比电信号宽;云闪的光信号在上述特征参数的滞后量、上升沿时间和脉宽时间差要比地闪回击放电大。从闪电光电信号时域信号特征的角度,利用BP人工神经网络,对闪电类型进行了模式识别研究。总体识别结果基本上能够满足要求,但是由于云闪放电过程比较复杂,获得的数据较少,所以对云闪识别的效果并不理想。     

Quaternion-based improved LPP method for color face recognition

In recent years, pattern recognition and computer vision have increasingly become the focus of research. Locality preserving projection (LPP) is a very important learning method in these two fields and has been widely used. Using LPP to perform face recognition, we usually can get a high accuracy. However, the face recognition application of LPP suffers from a number of problems and the small sample size is the most famous one. Moreover, though the face image is usually a color image, LPP cannot sufficiently exploit the color and we should first convert the color image into the gray image and then apply LPP to it. Transforming the color image into the gray image will cause a serious loss of image information. In this paper, we first use the quaternion to represent the color pixel. As a result, an original training or test sample can be denoted as a quaternion vector. Then we apply LPP to the quaternion vectors to perform feature extraction for the original training and test samples. The devised quaternion-based improved LPP method is presented in detail. Experimental results show that our method can get a higher classification accuracy than other methods.     

Mechanical and dynamic aspects of voice production as related to voice therapy and phonosurgery

Laryngeal framework surgery can change the position and tensionof the vocal folds safely without direct surgical intervention in the vocal fold proper. Some 23 years of experience with phonosurgery have proved its usefulness in treating dysphonia related to unilateral vocal fold paralysis, vocal fold atrophy, and pitch-related dysphonias. Meanwhile, much information about the mechanism of voice production has been obtained through intraoperative findings of voice and fiberscopic examination of the larynx . Based on such knowledge together with information obtained through model experiments, the human vocal organ was reconsidered mainly from the mechanical view point, and the roles of voice therapy and singing pedagogy were discussed in relation to phonosurgery. The vocal organ may not be an ideal musical organ and is rather vulnerable, but its potential is enormous.     

A study of the effectiveness of voice therapy in the treatment of 45 patients with nonorganic dysphonia

Forty-five patients diagnosed as having nonorganic dysphonia were assigned in rotation to 1 of 3 groups. Patients in group 1 received no treatment and acted as a control group. Patients in groups 2 and 3 received a program of indirect therapy and direct with indirect therapy, respectively. A range of qualitative and quantitative measures were carried out on all patients before and after treatment to evaluate change in voice quality over time. Results revealed a significant difference between the 3 treatment groups in the amount of change for the voice severity, electrolaryngograph, and shimmer measurements and on ratings provided by a patient questionnaire (P<0.05). However, other measures failed to show significant differences between the 3 groups. Most of the patients (86%) in group 1 showed no significant change on any of the measures. Some patients in treatment group 2 (46%) showed significant change in voice quality. Fourteen out of 15 patients (93%) in treatment group showed significant changes in voice quality.     

药剂颜色标准的谱识别方法

提出一种药剂颜色标准的谱识别新方法 ,该方法突破了传统的三刺激值测色模式。提出了用光谱特征及非固定的背景模式 ,代替三刺激值及CIE测量模式 ,建立了良好的判别函数 ,适于药剂颜色标准的客观检验与定级 ,结果令人满意。     

一种基于模式识别的多路盲语音提取方法

盲分离算法能在缺少混合系统参数的条件下仅由观测信号估计初始源,但分离信号存在固有的排列模糊性,这往往导致两次批处理过程中同一信号"对不准",因此很难获得连续的源信号。本文针对盲声源分离中存在的相同问题,根据语音和其他音频信号的特征差异,提出一种修正的自相关函数并以其值作为一个特征基元来表征声音信号的时序相关特性,同时用平均声门波形状参数作为另一个特征基元来表征语音产生的生理效应。以这两个参数作为识别不同音频信号的二维模式特征,采用一种模糊聚类算法提取多路盲分离语音。本方法有效克服了批处理盲声源分离中的信号排列顺序的不确定性,并通过选择合适的阈值提取多路连续语音。仿真给出了5路混合音频信号中盲提取两路连续语音的实验结果。     

神经网络在声发射信号模式识别中的应用

介绍了人工神经网络中的BP网络、RBF网络、Hamming网络、BP－Hamming网络在声发射信号模式识别中的应用现状，并对这些方法的优缺点进行了比较。     

Coping strategies, personality, and voice quality in patients with vocal fold nodules and polyps

Emotional state affects the physiological mechanism involved inphonation. Differences in acoustical parameters of the voice under stress have been attributed to the coping mechanism used, which is based on the individual's perception of the situation. This study examines the relationship between coping strategies, personality, and voice in female subjects, ranging in age from 19.3–55.7 years, diagnosed with vocal nodules or polyps. The differences between coping strategies and personality are examined and compared with another group with no history of voice pathology. The relationship of personality and coping strategies to voice quality variables is reported. Results show that patients use emotional coping strategies more and cognitive coping strategies less than the comparison group. Type of voice pathology was found to be related to dominance, and a number of coping and personality variables were found to correlate significantly with voice quality.     

Data processing in BOTDR distributed strain measurement based on pattern recognition

As a distributed fiber optic sensor able to monitor strain distribution within dozens of miles, BOTDR is widely applied in structural health monitoring (SHM). However, the difficulty of data processing has been in the way of health monitoring of civil structures and hence an obstacle against BOTDR’s development. In order to realize the rapid processing of distributed strain data, the strain measurement line was divided into a series of waveform units to confirm whether waveform units are normal or not by pattern recognition while taking both mean and standard deviation of characteristic vector into consideration, as well as combine neighboring abnormal units as abnormal area and give evaluation and warning to this area by the correspondence between waveforms and fiber deformation. The application of data processing in distributed monitoring of a certain tunnel showed that the abnormal area can be located fast and accurately and the deformation of optical fiber and structure can be evaluated with this technology.     

Effects of HearFones on speaking and singing voice quality

HearFones (HF) have been designed to enhance auditory feedback during phonation. This study investigated the effects of HF (1) on sound perceivable by the subject, (2) on voice quality in reading and singing, and (3) on voice production in speech and singing at the same pitch and sound level.

Test 1: Text reading was recorded with two identical microphones in the ears of a subject. One ear was covered with HF, and the other was free. Four subjects attended this test. Tests 2 and 3: A reading sample was recorded from 13 subjects and a song from 12 subjects without and with HF on. Test 4: Six females repeated [pa:p:a] in speaking and singing modes without and with HF on same pitch and sound level.

Long-term average spectra were made (Tests 1–3), and formant frequencies, fundamental frequency, and sound level were measured (Tests 2 and 3). Subglottic pressure was estimated from oral pressure in [p], and simultaneously electroglottography (EGG) was registered during voicing on [a:] (Test 4). Voice quality in speech and singing was evaluated by three professional voice trainers (Tests 2–4).

HF seemed to enhance sound perceivable at the whole range studied (0–8 kHz), with the greatest enhancement (up to ca 25 dB) being at 1–3 kHz and at 4–7 kHz. The subjects tended to decrease loudness with HF (when sound level was not being monitored). In more than half of the cases, voice quality was evaluated “less strained” and “better controlled” with HF. When pitch and loudness were constant, no clear differences were heard but closed quotient of the EGG signal was higher and the signal more skewed, suggesting a better glottal closure and/or diminished activity of the thyroarytenoid muscle.     

The relationship among voice onset, voice quality, and fundamental frequency: a dynamical perspective

In dynamical motor theory, skill acquisition occurs as a modification of preexisting coordination patterns or attractor states. The purpose of this study was to assess how different levels of voice onset, voice quality, and fundamental frequency (F₀) combine to form the attractor states common to voice motor control. Three levels of voice onset (glottal, simultaneous, and breathy), voice quality (modal speech, mixed, and falsetto), and fundamental frequency (low, mid, and high) were manipulated by vocally untrained, female subjects. Percent correct of acquisition trials and self-report of effort were used as measures of stable phonations indicative of an attractor state. Using intensity as a covariate, the results provided support for two of the three predicted triads representing attractor states in female speakers: (1) glottal onset/modal speech quality/low F₀; and (2) breathy onset/falsetto quality/high F₀. The results of this study suggest that certain parameters of voice motor control, such as onset, quality, and F₀, exist as part of a dynamical system that can be identified and manipulated in voice motor acquisition and learning.     

The clinical voice laboratory: Clinical application of voice research

In the past decade the number of voice laboratories has increased dramatically. Their primary mission is to enhance patient care by the application of knowledge gained from basic research. They also are dedicated to further improvement of diagnostic and therapeutic resources. The strength of the voice laboratory lies in collaboration between the clinician and the scientist.     

Color component 3D Arnold transform for polychromatic pattern recognition

We propose a novel method for polychromatic pattern recognition based on color component 3D Arnold transform. Three color components (for example RGB) are first transformed into three chaotic images by the use of 3D Arnold transform. And then any one of the chaotic images is chosen as the input image of the JTC to be recognized. As a result, strong color discrimination capability is achieved and common color images as well as some special color images can be recognized, while still preserving compact system and easier analysis of the output. Numerical results demonstrate the feasibility and effectiveness of the proposed method.     

Pattern recognition in muscle misuse voice disorders:How I do it

The diagnosis of the patient with a muscle misuse voice disorder can be a complex process. The dysphonia is usually caused by problems stemming from a number of interacting factors that may include habitual vocal technique and postural use, vocal behavior, emotion, manifestations of gastroesophageal refux, neuromuscular abnormalities, and associated organic mucosal disease. Sorting out the relative importance of the various factors is the first step towards planning an effective treatment program. This article addresses the difficulties caused by trying to classify dysphonia too rigidly, and presents a strategy for collecting the necessary information in a manner that facilitates the development of effective tools for clinical decision making. For each dysphonic patient, a pattern of causation will emerge in a way that helps the clinician to disentangle the interrelated factors.     

Documentation of progress in voice therapy: perceptual, acoustic, and laryngostroboscopic findings pretherapy and posttherapy

The effect of voice therapy in a group of chronically dysphonic patients with diverse diagnoses was studied according to the normal clinical procedure. The results were evaluated by perceptual rating, acoustic analysis, and the assessment of laryngostroboscopic recordings. Although the group effects for the differences between posttherapy and pretherapy data were clearly significant, the effects of voice therapy for the individual patients were divergent. For each of the three evaluation methods, a significant improvement was found for about 40% to 50% of the patients. The diversity of the therapy outcome among the patients could not be explained by the pretherapy status nor by age, gender, or diagnosis groups. In general, the perceptual ratings and the acoustic parameters from the baseline data were clearly correlated. However, these characterizations of the voice were only moderately correlated with the visual evaluation of the vocal fold vibrations. Relations among the three evaluation tools for the changes caused by voice therapy were very weak. The low correlation among the three methods suggests that a multidimensional evaluation of the voice is necessary to give a complete picture of the therapy outcome.     

Learning-induced pattern classification in a chaotic neural network

In this Letter, we propose a Hebbian learning rule with passive forgetting (HLRPF) for use in a chaotic neural network (CNN). We then define the indices based on the Euclidean distance to investigate the evolution of the weights in a simplified way. Numerical simulations demonstrate that, under suitable external stimulations, the CNN with the proposed HLRPF acts as a fuzzy-like pattern classifier that performs much better than an ordinary CNN. The results imply relationship between learning and recognition.