Ten Years of Research on Automatic Voice and Speech Analysis of People With Alzheimer's Disease and Mild Cognitive Impairment: A Systematic Review Article.

Background: The field of voice and speech analysis has become increasingly popular over the last 10 years, and articles on its use in detecting neurodegenerative diseases have proliferated. Many studies have identified characteristic speech features that can be used to draw an accurate distinction between healthy aging among older people and those with mild cognitive impairment and Alzheimer's disease. Speech analysis has been singled out as a cost-effective and reliable method for detecting the presence of both conditions. In this research, a systematic review was conducted to determine these features and their diagnostic accuracy. Methods: Peer-reviewed literature was located across multiple databases, involving studies that apply new procedures of automatic speech analysis to collect behavioral evidence of linguistic impairments along with their diagnostic accuracy on Alzheimer's disease and mild cognitive impairment. The risk of bias was assessed by using JBI and QUADAS-2 checklists. Results: Thirty-five papers met the inclusion criteria; of these, 11 were descriptive studies that either identified voice features or explored their cognitive correlates, and the rest were diagnostic studies. Overall, the studies were of good quality and presented solid evidence of the usefulness of this technique. The distinctive acoustic and rhythmic features found are gathered. Most studies record a diagnostic accuracy over 88% for Alzheimer's and 80% for mild cognitive impairment. Conclusion: Automatic speech analysis is a promising tool for diagnosing mild cognitive impairment and Alzheimer's disease. The reported features seem to be indicators of the cognitive changes in older people. The specific features and the cognitive changes involved could be the subject of further research.

A Prototype for the Voice Analysis Diagnosis of Alzheimer's Disease.

BACKGROUND: Speech variations enable us to map the performance of cognitive processes of syntactic, semantic, phonological, and articulatory planning and execution. Speaking is one of the first functions to be affected by neurodegenerative complaints such as Alzheimer's disease (AD), which makes the speech a highly promising biomarker for detecting the illness before the first preclinical symptoms appear. OBJECTIVE: This paper has sought to develop and validate a technological prototype that adopts an automated approach to speech analysis among older people. METHODS: It uses a mathematical algorithm based on certain discriminatory variables to estimate the probability of developing AD. RESULTS AND CONCLUSION: This device may be used at a preclinical stage by non-expert health professionals to determine the likelihood of the onset of AD.

The timely expression of coherence helps cause the right impression / Expresar coherencia en el momento preciso beneficia a la impresión causada

An analysis was conducted on the modulating role that the emotional coherence between verbal and non-verbal information plays on the formation of impressions. The study involved 301 subjects who made inferences on a woman’s personality based on verbal information on her life (positive, negative), the emotional coherence between verbal and nonverbal information (coherent, neutral, incoherent), and the type of coding, referring to the moment when the verbal and non-verbal information was presented to them (simultaneously, separately). The results showed that when the information is positive, coherent and the coding has been made separately, the person is perceived to be more stable, pleasant and sociable. The results are discussed, along with their implications for the adaptive processes present in natural contexts

Se analizó el papel modulador de la coherencia emocional entre la información verbal y no verbal en la formación de impresiones. Participaron 301 sujetos que realizaron inferencias sobre la personalidad de una mujer a partir de información verbal sobre su vida (positiva, negativa), la coherencia emocional entre la información verbal y no verbal (coherente, neutral, incoherente) y el tipo de codificación, referida al momento en el que se les presentó la información verbal y no verbal (simultánea, separada). Los resultados mostraron que cuando la información es positiva, coherente y la codificación se ha realizado por separado, se considera más estable, amable y sociable a la persona percibida. Se discuten los resultados y su implicación en los procesos adaptativos presentes en los contextos naturales

Improvement of encoding and retrieval in normal and pathological aging with word-picture paradigm.

OBJECTIVES: During the aging process, there is a progressive deficit in the encoding of new information and its retrieval. Different strategies are used in order to maintain, optimize or diminish these deficits in people with and without dementia. One of the classic techniques is paired-associate learning (PAL), which is based on improving the encoding of memories, but it has yet to be used to its full potential in people with dementia. In this study, our aim is to corroborate the importance of PAL tasks as instrumental tools for creating contextual cues, during both the encoding and retrieval phases of memory. Additionally, we aim to identify the most effective form of presenting the related items. METHOD: Pairs of stimuli were shown to healthy elderly people and to patients with moderate and mild Alzheimer's disease. The encoding conditions were as follows: word/word, picture/picture, picture/word, and word/picture. RESULTS: Associative cued recall of the second item in the pair shows that retrieval is higher for the word/picture condition in the two groups of patients with dementia when compared to the other conditions, while word/word is the least effective in all cases. CONCLUSION: These results confirm that PAL is an effective tool for creating contextual cues during both the encoding and retrieval phases in people with dementia when the items are presented using the word/picture condition. In this way, the encoding and retrieval deficit can be reduced in these people.

Speech in Alzheimer's disease: can temporal and acoustic parameters discriminate dementia?

AIMS: The study explores how speech measures may be linked to language profiles in participants with Alzheimer's disease (AD) and how these profiles could distinguish AD from changes associated with normal aging. METHODS: We analysed simple sentences spoken by older adults with and without AD. Spectrographic analysis of temporal and acoustic characteristics was carried out using the Praat software. RESULTS: We found that measures of speech, such as variations in the percentage of voice breaks, number of periods of voice, number of voice breaks, shimmer (amplitude perturbation quotient), and noise-to-harmonics ratio, characterise people with AD with an accuracy of 84.8%. DISCUSSION: These measures offer a sensitive method of assessing spontaneous speech output in AD, and they discriminate well between people with AD and healthy older adults. This method of evaluation is a promising tool for AD diagnosis and prognosis, and it could be used as a dependent measure in clinical trials.

El efecto de memoria congruente con el estado afectivo reconocimiento diferencial de palabras de tristeza y alegría / The mood congruence memory effect: Differential recognition of sadness and joy words

Los estudios sobre el efecto de congruencia con el estado de ánimo suelen utilizar muestras clínicas de personas depresivas, utilizan programas de inducción de afecto introspectivos, y miden la memoria con tareas de recuerdo libre. Nosotros pretendemos comprobar esta hipótesis induciendo dos estados de ánimo contrapuestos en 100 participantes sin patología. El objetivo fue estudiar la influencia de los estados de ánimo en el reconocimiento de palabras congruentes con dichos estados de ánimo. Para inducir los estados afectivos, utilizamos la asociación de imágenes y música con la dimensión de tristeza y de alegría. Después aprendieron palabras relacionadas con ambos estados emocionales. Encontramos efectos de interacción entre el tipo de estado afectivo inducido y el reconocimiento de las palabras emocionales, tanto en latencias como en índices de discriminación A'. Sin embargo, encontramos diferencias en el reconocimiento dependiendo del tipo de estado de ánimo. El efecto de congruencia con el estado de ánimo se produce en el procesamiento de palabras de la categoría de tristeza, pero no en las palabras de la categoría de alegría. Éstas tienen latencias más rápidas e índices de discriminación más altos, al margen del estado inducido experimentalmente (AU)

Studies on the mood congruence effect commonly used clinical samples of depressed people use affect induction programs introspective, and measure the memory with free recall tasks. We intend to verify this hypothesis induces two conflicting moods in 100 participants without pathology. The aim was to study the influence of mood on the recognition of words congruent with those moods. To induce affective states, we use the association of images and music with the dimension of sadness and joy. After they learned words related to the two emotional states. We found interaction effects between type of induced emotional state and recognition of emotional words in both latencies as indices of discrimination A '. However, we found differences in the recognition depending on the mood. The mood congruence effect occurs in the processing of words in the category of sadness, but not in the words of the category of joy. These latencies are faster and higher rates of discrimination, regardless of the experimentally induced state (AU)

Toma de decisiones en la anorexia nerviosa / No disponible

No disponible