基于支持向量机的神经元形态分类

针对神经元的空间几何形态特征分类问题以及神经元的生长预测问题进行了探讨.结合神经元的形态数据,分别建立了基于支持向量机的神经元形态分类模型、基于主成分分析和支持向量机的神经元分类模型以及基于遗传算法和RBF网络的神经元生长预测模型,在较合理的假设下,对各个模型进行求解,得到了较理想的结果.     

Performance effects on the voices of 10 choral tenors: Acoustic and perceptual findings

Trained choral tenors performed a series of vocal tasks before and after a “live” performance. Acoustic (perturbation, harmonic-to-noise ratio, pitch and amplitude ranges) and perceptual analyses (auditory and proprioceptive/kinesthetic) were undertaken to detect changes from pre- to postperformance. Individuality of response to the performance was revealed, with the majority of subjects showing vocal deterioration after performance. The most sensitive vocal tasks were the comfortably pitched notes, high soft notes, and the bottom notes in scale singing. The most sensitive acoustic measure in detecting change from pre- to postperformance was harmonic-to-noise ratio. In contrast to the demonstrated acoustic changes, no significant differences in perceptual ratings were evident after the performance. Perceptual ratings did not reflect the acoustic analysis results. The present study highlights the need to establish further normative data for the singing voice and to consider individual differences in vocal characteristics in future studies of the singing voice.     

Reliability in Perceptual Analysis of Voice Quality

This study focuses on speaking voice quality in male teachers (n = 35) and male actors (n = 36), who represent untrained and trained voice users, because we wanted to investigate normal and supranormal voices. In this study, both substantial and methodologic aspects were considered. It includes a method for perceptual voice evaluation, and a basic issue was rater reliability. A listening group of 10 listeners, 7 experienced speech-language therapists, and 3 speech-language therapist students evaluated the voices by 15 vocal characteristics using VA scales. Two sets of voice signals were investigated: text reading (2 loudness levels) and sustained vowel (3 levels). The results indicated a high interrater reliability for most perceptual characteristics. Connected speech was evaluated more reliably, especially at the normal level, but both types of voice signals were evaluated reliably, although the reliability for connected speech was somewhat higher than for vowels. Experienced listeners tended to be more consistent in their ratings than did the student raters. Some vocal characteristics achieved acceptable reliability even with a smaller panel of listeners. The perceptual characteristics grouped in 4 factors reflected perceptual dimensions.     

Inter-channel de-correlation for perceptual audio coding

Sound reproduction is evolving towards multi-channel systems with a growing number of channels. Consequently, high quality multi-channel codecs are required. Last generation perceptual audio codecs, represented by MPEG advanced audio coder (AAC), can efficiently code typical surround multi-channel material but may benefit from a previous block of inter-channel de-correlation, for certain audio recordings. These recordings present high correlation between non-symmetric channels, or correspond to loudspeaker arrangements different from surround, such as linear loudspeaker arrays. In order to valuate the advantages of this new coding approach, a multi-channel perceptual quality measure is developed.     

Methods for quantitative image quality evaluation of MRI parallel reconstructions: detection and perceptual difference model

Many reconstruction algorithms are being proposed for parallel magnetic resonance imaging (MRI), which uses multiple coils and subsampled k-space data, and a quantitative method for comparison of algorithms is sorely needed. On such images, we compared three methods for quantitative image quality evaluation: human detection, computer detection model and a computer perceptual difference model (PDM). One-quarter sampling and three different reconstruction methods were investigated: a regularization method developed by Ying et al., a simplified regularization method and an iterative method proposed by Pruessmann et al. Images obtained from a full complement of k-space data were also included as reference images. Detection studies were performed using a simulated dark tumor added on MR images of fresh bovine liver. Human detection depended strongly on reconstruction methods used, with the two regularization methods achieving better performance than the iterative method. Images were also evaluated using detection by a channelized Hotelling observer model and by PDM scores. Both predicted the same trends as observed from human detection. We are encouraged that PDM gives trends similar to that for human detection studies. Its ease of use and applicability to a variety of MRI situations make it attractive for evaluating image quality in a variety of MR studies.     

Acoustic and Perceptual Appraisal of Vocal Gestures in the Female Classical Voice

Long-term average spectra (LTAS) have identified features in the sounds of singers and have compared different vocal qualities based on energy changes that occur during different vocal tasks. In this study, we compared the perceptual ratings of vocal quality of expert pedagogues with acoustic measures performed on LTAS. Fifteen expert judges rated 24 samples with six repeats of six advanced singing students under two conditions: "optimal" (O), which represented the application of the maximal open throat technique; and "suboptimal" (SO), which represented the application of the reduced open throat technique. LTAS were performed on each singing sample, and two conventional assessments of peak energy height [singing power ratio (SPR)] and peak area [energy ratio (ER)] were calculated on each LTAS. Perceptual scores, SPR, and ER were rank ordered. We then compared perceptual rankings with rankings of acoustic measures (SPR and ER) to assess whether these acoustic measurements matched the perceptual judgments of vocal quality. Although we found the expected significant relationship between SPR and ER, there was no relationship between perceptual ratings of vocal samples or singers based on SPR or ER. These findings suggest that because LTAS measures are not consistent with perceptual ratings of vocal quality, such measurements cannot define a voice of quality. Future research with LTAS to assess vocal quality should consider alternative measures that are more sensitive to subtle differences in vocal parameters.     

Statistically robust evidence of stochastic resonance in human auditory perceptual system

In human perception, exogenous noise is known to yield a masking effect, i.e. an increase of the perceptual threshold relative to a stimulus acting on the same modality. However, somehow counter-intuitively, the opposite mechanism can occasionally occur: a decrease of the perceptual threshold for a non-vanishing, virtuous amount of noise. This mechanism, called stochastic resonance, is deemed to provide important information about the role of noise in the human brain. In this paper, we investigate stochastic resonance in a detection task in the auditory modality. Normal-hearing participants were asked to judge the presence of acoustic stimuli of different intensity and superimposed to different levels of white noise. The matrix-like outcomes of a behavioural experiment were fitted by a two-dimensional, noise-dependent psychometric function. The fit revealed a statistically significant stochastic resonance in 43% of the experimental runs. We conclude that, in the auditory modality, stochastic resonance is a tiny effect that, under conventional circumstances, is largely overrun by standard masking.     

A perceptual space for underwater man-made sounds towards target classification

This work is the second part in a series of studies about the auditory features for underwater target classification, focusing on man-made vehicle targets (i.e. submarines, patrol boats and large surface ships). A psychoacoustic method, which is suitable for a small number of samples, was used. An optimal model with three common dimensions, specificities and latent classes was selected on the basis of the dissimilarity ratings among representative sounds and with the use of an extended version of the multidimensional scaling algorithm CLASCAL. However, such a three-dimensional space could not absolutely separate targets, whereas the first dimension in the four-dimensional space discriminated the submarines, patrol boats and ships; thus, the four-dimensional space was superior in target classification. The stepwise regression method was used to establish the relationships between individual dimensions and typical auditory features. Results showed that the first dimension was represented by the linear combination of zero-crossing rate and spectral variation, whereas the second dimension was described by attack slope. The last two dimensions were not associated with any features, and they were proved to include meaningless data noises. Finally, through a contrastive analysis, the perceptual space obtained in this study was found to be a good ‘local’ representation of the space in the first part of the study series.