Feature selection for automatic analysis of emotional response based on nonlinear speech modeling suitable for diagnosis of Alzheimer׳s disease

Alzheimer׳s disease (AD) is the most common type of dementia among the elderly. This work is part of a larger study that aims to identify novel technologies and biomarkers or features for the early detection of AD and its degree of severity. The diagnosis is made by analyzing several biomarkers and conducting a variety of tests (although only a post-mortem examination of the patients’ brain tissue is considered to provide definitive confirmation). Non-invasive intelligent diagnosis techniques would be a very valuable diagnostic aid. This paper concerns the Automatic Analysis of Emotional Response (AAER) in spontaneous speech based on classical and new emotional speech features: Emotional Temperature (ET) and fractal dimension (FD). This is a pre-clinical study aiming to validate tests and biomarkers for future diagnostic use. The method has the great advantage of being non-invasive, low cost, and without any side effects. The AAER shows very promising results for the definition of features useful in the early diagnosis of AD.

Melodic Analysis of Speech Method applied to Spanish and Catalan

In this paper, we present the Melodic Analysis of Speech method (MAS) that enables us to carry out complete and objective descriptions of a language's intonation, from a phonetic (melodic) point of view as well as from a phonological point of view. It is based on the acoustic-perceptive method by Cantero (2002), which has already been used in research on prosody in different languages. In this case, we present the results of its application in Spanish and Catalan.

An in-depth analysis of real and perceived barriers to speech and language program participation for children with speech and language delays : a question of barriers to service?

The current study investigated the effects that barriers (both real and perceived) had on participation and completion of speech and language programs for preschool children with communication delays. I compared 36 families of preschool children with an identified communication delay that have completed services (completers) to 13 families that have not completed services (non-completers) prescribed by Speech and Language professionals. Data findings reported were drawn from an interview with the mother, a speech and language assessment of the child, and an extensive package of measures completed by the mother. Children ranged in age from 32 to 71 mos. These data were collected as part of a project funded by the Canadian Language and Literacy Research Networks of Centres of Excellence. Findings suggest that completers and non-completers shared commonalities in a number of parenting characteristics but differed significantly in two areas. Mothers in the noncompleting group were more permissive and had lower maternal education than mothers in the completing families. From a systemic standpoint, families also differed in the number of perceived barriers to treatment experienced during their time with Speech Services Niagara. Mothers in the non-completing group experienced more perceived barriers to treatment than completing mothers. Specifically, these mothers perceived more stressors and obstacles that competed with treatment, perceived more treatment demands and they perceived the relevance of treatment as less important than the completing group. Despite this, the findings suggest that non-completing families were 100% satisfied with services. Contrary to predictions, there were no significant differences in child characterisfics and economic characteristics between completers and non-completers. The findings in this study are considered exploratory and tentative due to the small sample size.

Median filtering: structure analysis and application

Median filtering is a simple digital non—linear signal smoothing operation in which median of the samples in a sliding window replaces the sample at the middle of the window. The resulting filtered sequence tends to follow polynomial trends in the original sample sequence. Median filter preserves signal edges while filtering out impulses. Due to this property, median filtering is finding applications in many areas of image and speech processing. Though median filtering is simple to realise digitally, its properties are not easily analysed with standard analysis techniques,

Spectral clustering independent component analysis for tissue classification from brain MRI

A spectral angle based feature extraction method, Spectral Clustering Independent Component Analysis (SC-ICA), is proposed in this work to improve the brain tissue classification from Magnetic Resonance Images (MRI). SC-ICA provides equal priority to global and local features; thereby it tries to resolve the inefficiency of conventional approaches in abnormal tissue extraction. First, input multispectral MRI is divided into different clusters by a spectral distance based clustering. Then, Independent Component Analysis (ICA) is applied on the clustered data, in conjunction with Support Vector Machines (SVM) for brain tissue analysis. Normal and abnormal datasets, consisting of real and synthetic T1-weighted, T2-weighted and proton density/fluid-attenuated inversion recovery images, were used to evaluate the performance of the new method. Comparative analysis with ICA based SVM and other conventional classifiers established the stability and efficiency of SC-ICA based classification, especially in reproduction of small abnormalities. Clinical abnormal case analysis demonstrated it through the highest Tanimoto Index/accuracy values, 0.75/98.8%, observed against ICA based SVM results, 0.17/96.1%, for reproduced lesions. Experimental results recommend the proposed method as a promising approach in clinical and pathological studies of brain diseases

Developing a Child Friendly Text-to-Speech System

This paper discusses the implementation details of a child friendly, good quality, English text-to-speech (TTS) system that is phoneme-based, concatenative, easy to set up and use with little memory. Direct waveform concatenation and linear prediction coding (LPC) are used. Most existing TTS systems are unit-selection based, which use standard speech databases available in neutral adult voices.Here reduced memory is achieved by the concatenation of phonemes and by replacing phonetic wave files with their LPC coefficients. Linguistic analysis was used to reduce the algorithmic complexity instead of signal processing techniques. Sufficient degree of customization and generalization catering to the needs of the child user had been included through the provision for vocabulary and voice selection to suit the requisites of the child. Prosody had also been incorporated. This inexpensive TTS systemwas implemented inMATLAB, with the synthesis presented by means of a graphical user interface (GUI), thus making it child friendly. This can be used not only as an interesting language learning aid for the normal child but it also serves as a speech aid to the vocally disabled child. The quality of the synthesized speech was evaluated using the mean opinion score (MOS).

Electrophysiological analysis of the olfactory signal transduction cascade in the hawkmoth Manduca sexta

Neben der Verbreitung von gefährlichen Krankheiten sind Insekten für enorme agrarwirtschaftliche Schäden verantwortlich. Ein Großteil der Verhaltensweisen bei Insekten wird über den Geruchssinn gesteuert, der somit einen möglichen Angriffspunkt zur Bekämpfung von Schadinsekten darstellt. Hierzu ist es allerdings nötig, die Mechanismen der olfaktorischen Signalübertragung im Detail zu verstehen. Neben den duftstoffbindenden olfaktorischen Rezeptoren spielt hier auch ein konservierter Korezeptor (Orco) eine entscheidende Rolle. Inwieweit bei diesen Proteinen ionotrope bzw. metabotrope Prozesse involviert sind ist bislang nicht vollständig aufgeklärt. Um weitere Einzelheiten aufzuklären wurden daher Einzelsensillenableitungen am Tabakschwärmer Manduca sexta durchgeführt. Orco-Agonisten und Antagonisten wurden eingesetzt, um die Funktion des Korezeptors besser zu verstehen. Bei dem Einsatz des Orco-Agonisten VUAA1 konnte keine Verstärkung der Pheromonantworten bzw. eine Sensitivierung beobachtet werden, wie im Falle einer ionotropen Signalweiterleitung zu erwarten gewesen wäre. Ein ionotroper Signalweg über den OR/Orco-Komplex in M. sexta ist daher unwahrscheinlich. Der Orco-Antagonist OLC15 beeinflusste die gleichen Parameter wie VUAA1 und konnte die von VUAA1 generierte Spontanaktivität blocken. Daher ist es wahrscheinlich, dass dieser einen spezifischen Orco-Blocker darstellt. Sowohl VUAA1 als auch OLC15 hatten großen Effekt auf die langanhaltende Pheromonantwort, welches die Vermutung nahelegt, dass Orco modulierend auf die Sensitivität der Nervenzelle einwirkt. Von OLC15 abweichende Effekte durch die getesteten Amiloride HMA und MIA auf die Pheromonantwort lassen nicht auf eine spezifische Wirkung dieser Agenzien auf Orco schließen und zusätzliche Wirkorte sind anzunehmen. Um die These eines metabotropen Signalwegs zu überprüfen wurde ebenfalls der G-Protein-Blocker GDP-β-S eingesetzt. Alle Parameter der Pheromonantwort die innerhalb der ersten Millisekunden analysiert wurden wiesen eine Reduktion der Sensitivität auf. Im Gegensatz dazu hatte GDP-β-S keinen Effekt auf die langanhaltende Pheromonantwort. Somit scheint ausschließlich die schnelle Pheromonantwort über einen Ligand-bindenden G-Protein-gesteuerten Rezeptor gesteuert zu werden.

Analysis of the consistency of alphabet symbol/speech sound correspondence in three basal reader series

This paper reviews a study to analyze the number of times alphabet symbols occur in three commonly used basal reader series.

An examination of the appropriateness of the CID grammatical analysis of elicted language as an instrument to compare language acquisition in deaf children enrolled in cued speech vs. oral and signed english programs

This paper discusses a study to compare test results of the CID GAEL test among hearing impaired children who are enrolled in cued speech vs. oral vs. signed english programs.

The relation between intelligibility and the acoustic characteristics of deaf speech: An acoustic analysis of the vowels /i/ and /aw/, and nasals

This paper discusses a study that examined acoustic measures and the relationship to speech intelligibility of children with cochlear implants.

Phoneme analysis of cochlear implant recipients' responses to CNC words using the MPEAK and SPEAK speech coding strategies of the Nucleus cochlear implant system

This paper discusses a study done to determine how cochlear implant users perceive speech sounds using MPEAK or SPEAK speech coding strategy.

From dichotic listening to the irrelevant sound effect: a behavioural and neuroimaging analysis of the processing of unattended speech

The assumption that ignoring irrelevant sound in a serial recall situation is identical to ignoring a non-target channel in dichotic listening is challenged. Dichotic listening is open to moderating effects of working memory capacity (Conway et al., 2001) whereas irrelevant sound effects (ISE) are not (Beaman, 2004). A right ear processing bias is apparent in dichotic listening, whereas the bias is to the left ear in the ISE (Hadlington et al., 2004). Positron emission tomography (PET) imaging data (Scott et al., 2004, submitted) show bilateral activation of the superior temporal gyrus (STG) in the presence of intelligible, but ignored, background speech and right hemisphere activation of the STG in the presence of unintelligible background speech. It is suggested that the right STG may be involved in the ISE and a particularly strong left ear effect might occur because of the contralateral connections in audition. It is further suggested that left STG activity is associated with dichotic listening effects and may be influenced by working memory span capacity. The relationship of this functional and neuroanatomical model to known neural correlates of working memory is considered.

Comparison of extrasystolic ECG signal classifiers using discrete wavelet transforms

This work compares and contrasts results of classifying time-domain ECG signals with pathological conditions taken from the MITBIH arrhythmia database. Linear discriminant analysis and a multi-layer perceptron were used as classifiers. The neural network was trained by two different methods, namely back-propagation and a genetic algorithm. Converting the time-domain signal into the wavelet domain reduced the dimensionality of the problem at least 10-fold. This was achieved using wavelets from the db6 family as well as using adaptive wavelets generated using two different strategies. The wavelet transforms used in this study were limited to two decomposition levels. A neural network with evolved weights proved to be the best classifier with a maximum of 99.6% accuracy when optimised wavelet-transform ECG data wits presented to its input and 95.9% accuracy when the signals presented to its input were decomposed using db6 wavelets. The linear discriminant analysis achieved a maximum classification accuracy of 95.7% when presented with optimised and 95.5% with db6 wavelet coefficients. It is shown that the much simpler signal representation of a few wavelet coefficients obtained through an optimised discrete wavelet transform facilitates the classification of non-stationary time-variant signals task considerably. In addition, the results indicate that wavelet optimisation may improve the classification ability of a neural network. (c) 2005 Elsevier B.V. All rights reserved.