Computerized analysis of speech and language to identify psycholinguistic correlates of frontotemporal lobar degeneration

A novel speech analysis algorithm to detect cognitive impairment in a Spanish population

Objective

Early detection of cognitive impairment in the elderly is crucial for diagnosis and appropriate care. Brief, cost-effective cognitive screening instruments are needed to help identify individuals who require further evaluation. This study presents preliminary data on a new screening technology using automated voice recording analysis software in a Spanish population.

Method

Data were collected from 174 Spanish-speaking individuals clinically diagnosed as cognitively normal (CN, n = 87) or impaired (mild cognitive impairment [MCI], n = 63; all-cause dementia, n = 24). Participants were recorded performing four common language tasks (Animal fluency, alternating fluency [sports and fruits], phonemic "F" fluency, and Cookie Theft Description). Recordings were processed via text-transcription and digital-signal processing techniques to capture neuropsychological variables and audio characteristics. A training sample of 122 subjects with similar demographics across groups was used to develop an algorithm to detect cognitive impairment. Speech and task features were used to develop five independent machine learning (ML) models to compute scores between 0 and 1, and a final algorithm was constructed using repeated cross-validation. A socio-demographically balanced subset of 52 participants was used to test the algorithm. Analysis of covariance (ANCOVA), covarying for demographic characteristics, was used to predict logistically-transformed algorithm scores.

Results

Mean logit algorithm scores were significantly different across groups in the testing sample (p < 0.01). Comparisons of CN with impaired (MCI + dementia) and MCI groups using the final algorithm resulted in an AUC of 0.93/0.90, with overall accuracy of 88.4%/87.5%, sensitivity of 87.5/83.3, and specificity of 89.2/89.2, respectively.

Conclusion

Findings provide initial support for the utility of this automated speech analysis algorithm as a screening tool for cognitive impairment in Spanish speakers. Additional study is needed to validate this technology in larger and more diverse clinical populations.

Speech silence character as a diagnostic biomarker of early cognitive decline and its functional mechanism: a multicenter cross-sectional cohort study

BACKGROUND

Language deficits frequently occur during the prodromal stages of Alzheimer's disease (AD). However, the characteristics of linguistic impairment and its underlying mechanism(s) remain to be explored for the early diagnosis of AD.

METHODS

The percentage of silence duration (PSD) of 324 subjects was analyzed, including patients with AD, amnestic mild cognitive impairment (aMCI), and normal controls (NC) recruited from the China multi-center cohort, and the diagnostic efficiency was replicated from the Pitt center cohort. Furthermore, the specific language network involved in the fragmented speech was analyzed using task-based functional magnetic resonance.

RESULTS

In the China cohort, PSD increased significantly in aMCI and AD patients. The area under the curve of the receiver operating characteristic curves is 0.74, 0.84, and 0.80 in the classification of NC/aMCI, NC/AD, and NC/aMCI+AD. In the Pitt center cohort, PSD was verified as a reliable diagnosis biomarker to differentiate mild AD patients from NC. Next, in response to fluency tasks, clusters in the bilateral inferior frontal gyrus, precentral gyrus, left inferior temporal gyrus, and inferior parietal lobule deactivated markedly in the aMCI/AD group (cluster-level P < 0.05, family-wise error (FWE) corrected). In the patient group (AD+aMCI), higher activation level of the right pars triangularis was associated with higher PSD in in both semantic and phonemic tasks.

CONCLUSIONS

PSD is a reliable diagnostic biomarker for the early stage of AD and aMCI. At as early as aMCI phase, the brain response to fluency tasks was inhibited markedly, partly explaining why PSD was elevated simultaneously.

A Systematic Review of Expressive and Receptive Prosody in People With Dementia

Purpose This review was designed to provide a systematic overview of prosody in people with a primary diagnosis of dementia (PwD) and evaluate the potential use of prosodic features for diagnosis of dementia. Method A systematic search of five databases was conducted using Medical Subject Headings and keywords. Studies included in the review were evaluated for their methodological quality using the modified Joanna Briggs Institute checklist. Results A total of 14 articles were identified as being relevant for this review. Among the 14 articles, the methodological quality ranged, with eight rated as weak, four rated as moderate, and two rated as strong. Ten of the 14 articles had people with Alzheimer's disease (AD) as participants, and the remaining four had people with frontotemporal dementia as participants. Four articles focused on receptive prosody, another six focused on expressive prosody, and the remaining four articles were investigations into both. The 14 articles presented inconsistent findings, and various tasks were used to measure prosodic features in PwD in the articles. Prosody was studied as a diagnostic tool for dementia in four of the articles, all of which were based on expressive prosody in individuals with AD. Among the four articles, three proposed the use of automatic speech analysis for diagnosis of AD. Conclusions This review demonstrates that prosody in PwD is an underinvestigated area. In particular, it was concerning that most articles were of weak methodological quality. Nevertheless, it was found that prosody may be a potential diagnostic tool for assessing dementia. More studies that replicate the existing studies and those with stronger methodology are needed to confirm that receptive and/or expressive prosody can be used for dementia diagnosis.

When it is not primary progressive aphasia: A scoping review of spoken language impairment in other neurodegenerative dementias

BACKGROUND

Progressive difficulties with spoken language occur across the spectrum of degenerative dementia. When not a primary presenting and dominant symptom, language difficulties may be overlooked in favor of more prominent cognitive, behavior, or motor deficits. The aim of this scoping review is to examine the extent and nature of the research evidence describing (1) the spoken language impairments found in non-language led dementias, (2) their impact on everyday living, and (3) the reported language interventions.

METHODS

We searched PubMed, MEDLINE, OVID-EMBASE, PsycINFO, and SpeechBITE using terms related to spoken language for the following dementia types: Parkinson's disease dementia (PDD), dementia with Lewy bodies (DLB), progressive supranuclear palsy (PSP), cortico-basal syndrome (CBS), behavior variant frontotemporal dementia (bvFTD), early-onset Alzheimer's disease (EOAD), posterior cortical atrophy (PCA), and motor neuron disease associated with FTD (MND+FTD). Risk of bias was assessed with the QualSyst tool.

RESULTS

Seventy-three eligible studies were included. A wide range of spoken language impairments were reported, involving both linguistic (e.g., syntactic processing) and other cognitive (e.g., sustained attention) underlying mechanisms. Although the severity of these deficits was scarcely reported, in some cases they manifested as non-fluent, dynamic, and global aphasias. No papers in the review described either the impact of these language impairments on everyday living or language therapies to treat them.

DISCUSSION

There is a need to understand better the level of disability produced by language impairment in people living with non-language-led dementias. Our findings suggest three calls for action: (1) research studies should assess the clinical relevance of any spoken language deficits examined, (2) both linguistic and cognitive underlying mechanisms should be fully described (to inform the design of effective language and behavioral interventions), and (3) trials of language therapy should be conducted in those groups of individuals where significant language impairment is proved.

Predicting Alzheimer's Disease from Spoken and Written Language Using Fusion-Based Stacked Generalization

The importance of automating the diagnosis of Alzheimer disease (AD) towards facilitating its early prediction has long been emphasized, hampered in part by lack of empirical support. Given the evident association of AD with age and the increasing aging population owing to the general well-being of individuals, there have been unprecedented estimated economic complications. Consequently, many recent studies have attempted to employ the language deficiency caused by cognitive decline in automating the diagnostic task via training machine learning (ML) algorithms with linguistic patterns and deficits. In this study, we aim to develop multiple heterogeneous stacked fusion models that harness the advantages of several base learning algorithms to improve the overall generalizability and robustness of AD diagnostic ML models, where we parallelly utilized two different written and spoken-based datasets to train our stacked fusion models. Further, we examined the effect of linking these two datasets to develop a hybrid stacked fusion model that can predict AD from written and spoken languages. Our feature spaces involved two widely used linguistic patterns: lexicosyntactics and character n-gram spaces. We firstly investigated lexicosyntactics of AD alongside healthy controls (HC), where we explored a few new lexicosyntactic features, then optimized the lexicosyntactic feature space by proposing a correlation feature selection technique that eliminates features based on their feature-feature inter-correlations and feature-target correlations according to a certain threshold. Our stacked fusion models establish benchmarks on both datasets with AUC of 98.1% and 99.47% for the spoken and written-based datasets, respectively, and corresponding accuracy and F1 score values around 95% on spoken-based dataset and around 97% on the written-based dataset. Likewise, the hybrid stacked fusion model on linked data presents an optimal performance with 99.2% AUC as well as accuracy and F1 score falling around 97%. In view of the achieved performance and enhanced generalizability of such fusion models over single classifiers, this study suggests replacing the initial traditional screening test with such models that can be embedded into an online format for a fully automated remote diagnosis.

Towards an Automatic Speech-Based Diagnostic Test for Alzheimer’s Disease

Automatic Speech Recognition (ASR) is widely used in many applications and tools. Smartphones, video games, and cars are a few examples where people use ASR routinely and often daily. A less commonly used, but potentially very important arena for using ASR, is the health domain. For some people, the impact on life could be enormous. The goal of this work is to develop an easy-to-use, non-invasive, inexpensive speech-based diagnostic test for dementia that can easily be applied in a clinician’s office or even at home. While considerable work has been published along these lines, increasing dramatically recently, it is primarily of theoretical value and not yet practical to apply. A large gap exists between current scientific understanding, and the creation of a diagnostic test for dementia. The aim of this paper is to bridge this gap between theory and practice by engineering a practical test. Experimental evidence suggests that strong discrimination between subjects with a diagnosis of probable Alzheimer’s vs. matched normal controls can be achieved with a combination of acoustic features from speech, linguistic features extracted from a transcription of the speech, and results of a mini mental state exam. A fully automatic speech recognition system tuned for the speech-to-text aspect of this application, including automatic punctuation, is also described.

Vocabulary Size Influences Spontaneous Speech in Native Language Users: Validating the Use of Automatic Speech Recognition in Individual Differences Research

Previous research has shown that vocabulary size affects performance on laboratory word production tasks. Individuals who know many words show faster lexical access and retrieve more words belonging to pre-specified categories than individuals who know fewer words. The present study examined the relationship between receptive vocabulary size and speaking skills as assessed in a natural sentence production task. We asked whether measures derived from spontaneous responses to everyday questions correlate with the size of participants' vocabulary. Moreover, we assessed the suitability of automatic speech recognition (ASR) for the analysis of participants' responses in complex language production data. We found that vocabulary size predicted indices of spontaneous speech: individuals with a larger vocabulary produced more words and had a higher speech-silence ratio compared to individuals with a smaller vocabulary. Importantly, these relationships were reliably identified using manual and automated transcription methods. Taken together, our results suggest that spontaneous speech elicitation is a useful method to investigate natural language production and that automatic speech recognition can alleviate the burden of labor-intensive speech transcription.

Development of Computer-Aided Semi-Automatic Diagnosis System for Chronic Post-Stroke Aphasia Classification with Temporal and Parietal Lesions: A Pilot Study

Survivors of either a hemorrhagic or ischemic stroke tend to acquire aphasia and experience spontaneous recovery during the first six months. Nevertheless, a considerable number of patients sustain aphasia and require speech and language therapy to overcome the difficulties. As a preliminary study, this article aims to distinguish aphasia caused from a temporoparietal lesion. Typically, temporal and parietal lesions cause Wernicke’s aphasia and Anomic aphasia. Differential diagnosis between Anomic and Wernicke’s has become controversial and subjective due to the close resemblance of Wernicke’s to Anomic aphasia when recovering. Hence, this article proposes a clinical diagnosis system that incorporates normal coupling between the acoustic frequencies of speech signals and the language ability of temporoparietal aphasias to delineate classification boundary lines. The proposed inspection system is a hybrid scheme consisting of automated components, such as confrontation naming, repetition, and a manual component, such as comprehension. The study was conducted involving 30 participants clinically diagnosed with temporoparietal aphasias after a stroke and 30 participants who had experienced a stroke without aphasia. The plausibility of accurate classification of Wernicke’s and Anomic aphasia was confirmed using the distinctive acoustic frequency profiles of selected controls. Accuracy of the proposed system and algorithm was confirmed by comparing the obtained diagnosis with the conventional manual diagnosis. Though this preliminary work distinguishes between Anomic and Wernicke’s aphasia, we can claim that the developed algorithm-based inspection model could be a worthwhile solution towards objective classification of other aphasia types.

A Review of Automated Speech and Language Features for Assessment of Cognitive and Thought Disorders

It is widely accepted that information derived from analyzing speech (the acoustic signal) and language production (words and sentences) serves as a useful window into the health of an individual's cognitive ability. In fact, most neuropsychological testing batteries have a component related to speech and language where clinicians elicit speech from patients for subjective evaluation across a broad set of dimensions. With advances in speech signal processing and natural language processing, there has been recent interest in developing tools to detect more subtle changes in cognitive-linguistic function. This work relies on extracting a set of features from recorded and transcribed speech for objective assessments of speech and language, early diagnosis of neurological disease, and tracking of disease after diagnosis. With an emphasis on cognitive and thought disorders, in this paper we provide a review of existing speech and language features used in this domain, discuss their clinical application, and highlight their advantages and disadvantages. Broadly speaking, the review is split into two categories: language features based on natural language processing and speech features based on speech signal processing. Within each category, we consider features that aim to measure complementary dimensions of cognitive-linguistics, including language diversity, syntactic complexity, semantic coherence, and timing. We conclude the review with a proposal of new research directions to further advance the field.

Automatic Assessment of Speech Impairment in Cantonese-speaking People with Aphasia

Aphasia is a common type of acquired language impairment resulting from dysfunction in specific brain regions. Analysis of narrative spontaneous speech, e.g., story-telling, is an essential component of standardized clinical assessment on people with aphasia (PWA). Subjective assessment by trained speech-language pathologists (SLP) have many limitations in efficiency, effectiveness and practicality. This paper describes a fully automated system for speech assessment of Cantonese-speaking PWA. A deep neural network (DNN) based automatic speech recognition (ASR) system is developed for aphasic speech by multi-task training with both in-domain and out-of-domain speech data. Story-level embedding and Siamese network are applied to derive robust text features, which can be used to quantify the difference between aphasic speech and unimpaired one. The proposed text features are combined with conventional acoustic features to cover different aspects of speech and language impairment in PWA. Experimental results show a high correlation between predicted scores and subject assessment scores. The best correlation value achieved with ASR-generated transcription is .827, as compared with .844 achieved with manual transcription. The Siamese network significantly outperforms story-level embedding in generating text features for automatic assessment.

Validated automatic speech biomarkers in primary progressive aphasia

Objective

To automatically extract and quantify specific disease biomarkers of prosody from the acoustic properties of speech in patients with primary progressive aphasia.

Methods

We analyzed speech samples from 59 progressive aphasic patients (non‐fluent/agrammatic = 15, semantic = 21, logopenic = 23; ages 50–85 years) and 31 matched healthy controls (ages 54–89 years). Using a novel, automated speech analysis protocol, we extracted acoustic measurements of prosody, including fundamental frequency and speech and silent pause durations, and compared these between groups. We then examined their relationships with clinical tests, gray matter atrophy, and cerebrospinal fluid analytes.

Results

We found a narrowed range of fundamental frequency in patients with non‐fluent/agrammatic variant aphasia (mean 3.86 ± 1.15 semitones) compared with healthy controls (6.06 ± 1.95 semitones; P < 0.001) and patients with semantic variant aphasia (6.12 ± 1.77 semitones; P = 0.001). Mean pause rate was significantly increased in the non‐fluent/agrammatic group (mean 61.4 ± 20.8 pauses per minute) and the logopenic group (58.7 ± 16.4 pauses per minute) compared to controls. In an exploratory analysis, narrowed fundamental frequency range was associated with atrophy in the left inferior frontal cortex. Cerebrospinal level of phosphorylated tau was associated with an acoustic classifier combining fundamental frequency range and pause rate (r = 0.58, P = 0.007). Receiver operating characteristic analysis with this combined classifier distinguished non‐fluent/agrammatic speakers from healthy controls (AUC = 0.94) and from semantic variant patients (AUC = 0.86).

Interpretation

Restricted fundamental frequency range and increased pause rate are characteristic markers of speech in non‐fluent/agrammatic primary progressive aphasia. These can be extracted with automated speech analysis and are associated with left inferior frontal atrophy and cerebrospinal phosphorylated tau level.

Computer-based evaluation of Alzheimer's disease and mild cognitive impairment patients during a picture description task

Introduction

We present a methodology to automatically evaluate the performance of patients during picture description tasks.

Methods

Transcriptions and audio recordings of the Cookie Theft picture description task were used. With 25 healthy elderly control (HC) samples and an information coverage measure, we automatically generated a population-specific referent. We then assessed 517 transcriptions (257 Alzheimer's disease [AD], 217 HC, and 43 mild cognitively impaired samples) according to their informativeness and pertinence against this referent. We extracted linguistic and phonetic metrics which previous literature correlated to early-stage AD. We trained two learners to distinguish HCs from cognitively impaired individuals.

Results

Our measures significantly (P < .001) correlated with the severity of the cognitive impairment and the Mini–Mental State Examination score. The classification sensitivity was 81% (area under the curve of receiver operating characteristics = 0.79) and 85% (area under the curve of receiver operating characteristics = 0.76) between HCs and AD and between HCs and AD and mild cognitively impaired, respectively.

Discussion

An automated assessment of a picture description task could assist clinicians in the detection of early signs of cognitive impairment and AD.

Automatic measurement of prosody in behavioral variant FTD

OBJECTIVE

To help understand speech changes in behavioral variant frontotemporal dementia (bvFTD), we developed and implemented automatic methods of speech analysis for quantification of prosody, and evaluated clinical and anatomical correlations.

METHODS

We analyzed semi-structured, digitized speech samples from 32 patients with bvFTD (21 male, mean age 63 ± 8.5, mean disease duration 4 ± 3.1 years) and 17 matched healthy controls (HC). We automatically extracted fundamental frequency (f0, the physical property of sound most closely correlating with perceived pitch) and computed pitch range on a logarithmic scale (semitone) that controls for individual and sex differences. We correlated f0 range with neuropsychiatric tests, and related f0 range to gray matter (GM) atrophy using 3T T1 MRI.

RESULTS

We found significantly reduced f0 range in patients with bvFTD (mean 4.3 ± 1.8 ST) compared to HC (5.8 ± 2.1 ST; p = 0.03). Regression related reduced f0 range in bvFTD to GM atrophy in bilateral inferior and dorsomedial frontal as well as left anterior cingulate and anterior insular regions.

CONCLUSIONS

Reduced f0 range reflects impaired prosody in bvFTD. This is associated with neuroanatomic networks implicated in language production and social disorders centered in the frontal lobe. These findings support the feasibility of automated speech analysis in frontotemporal dementia and other disorders.

Motor Speech Phenotypes of Frontotemporal Dementia, Primary Progressive Aphasia, and Progressive Apraxia of Speech

PURPOSE

Our purpose was to create a comprehensive review of speech impairment in frontotemporal dementia (FTD), primary progressive aphasia (PPA), and progressive apraxia of speech in order to identify the most effective measures for diagnosis and monitoring, and to elucidate associations between speech and neuroimaging.

METHOD

Speech and neuroimaging data described in studies of FTD and PPA were systematically reviewed. A meta-analysis was conducted for speech measures that were used consistently in multiple studies.

RESULTS

The methods and nomenclature used to describe speech in these disorders varied between studies. Our meta-analysis identified 3 speech measures which differentiate variants or healthy control-group participants (e.g., nonfluent and logopenic variants of PPA from all other groups, behavioral-variant FTD from a control group). Deficits within the frontal-lobe speech networks are linked to motor speech profiles of the nonfluent variant of PPA and progressive apraxia of speech. Motor speech impairment is rarely reported in semantic and logopenic variants of PPA. Limited data are available on motor speech impairment in the behavioral variant of FTD.

CONCLUSIONS

Our review identified several measures of speech which may assist with diagnosis and classification, and consolidated the brain-behavior associations relating to speech in FTD, PPA, and progressive apraxia of speech.

White Matter Disruption and Connected Speech in Non-Fluent and Semantic Variants of Primary Progressive Aphasia

Differential patterns of white matter disruption have recently been reported in the non-fluent (nfvPPA) and semantic (svPPA) variants of primary progressive aphasia (PPA). No single measure is sufficient to distinguish between the PPA variants, but connected speech allows for the quantification of multiple measures. The aim of the present study was to further investigate the white matter correlates associated with connected speech features in PPA. We examined the relationship between white matter metrics and connected speech deficits using an automated analysis of transcriptions of connected speech and diffusion tensor imaging in language-related tracts. Syntactic, lexical, and semantic features were automatically extracted from transcriptions of topic-directed interviews conducted with groups of individuals with nfvPPA or svPPA as well as with a group of healthy controls. A principal component analysis was performed in order to reduce the number of language measures and yielded a five-factor solution. The results indicated that nfvPPA patients differed from healthy controls on a syntactic factor, and svPPA patients differed from controls on two semantic factors. However, the patient groups did not differ on any factor. Moreover, a correlational analysis revealed that the lexical richness factor was significantly correlated with radial diffusivity in the left inferior longitudinal fasciculus, which suggests that semantic deficits in connected speech reflect a disruption of this ventral pathway, and which is largely consistent with the results of previous studies. Using an automated approach for the analysis of connected speech combined with probabilistic tractography, the present findings demonstrate that nfvPPA patients are impaired relative to healthy controls on syntactic measures and have increased radial diffusivity in the left superior longitudinal fasciculus, whereas the svPPA group was impaired on lexico-semantic measures relative to controls and showed increased radial diffusivity in the uncinate and inferior longitudinal fasciculus bilaterally.

Linguistic Features Identify Alzheimer's Disease in Narrative Speech

BACKGROUND

Although memory impairment is the main symptom of Alzheimer's disease (AD), language impairment can be an important marker. Relatively few studies of language in AD quantify the impairments in connected speech using computational techniques.

OBJECTIVE

We aim to demonstrate state-of-the-art accuracy in automatically identifying Alzheimer's disease from short narrative samples elicited with a picture description task, and to uncover the salient linguistic factors with a statistical factor analysis.

METHODS

Data are derived from the DementiaBank corpus, from which 167 patients diagnosed with "possible" or "probable" AD provide 240 narrative samples, and 97 controls provide an additional 233. We compute a number of linguistic variables from the transcripts, and acoustic variables from the associated audio files, and use these variables to train a machine learning classifier to distinguish between participants with AD and healthy controls. To examine the degree of heterogeneity of linguistic impairments in AD, we follow an exploratory factor analysis on these measures of speech and language with an oblique promax rotation, and provide interpretation for the resulting factors.

RESULTS

We obtain state-of-the-art classification accuracies of over 81% in distinguishing individuals with AD from those without based on short samples of their language on a picture description task. Four clear factors emerge: semantic impairment, acoustic abnormality, syntactic impairment, and information impairment.

CONCLUSION

Modern machine learning and linguistic analysis will be increasingly useful in assessment and clustering of suspected AD.

Vocabulary Size in Speech May Be an Early Indicator of Cognitive Impairment

Little is known about the relationship between mild cognitive impairment (MCI) and changes to language abilities. Here, we used the revised Hasegawa Dementia Scale (HDS-R) to identify suspected MCI in elderly individuals. We then analyzed written and spoken narratives to compare the language abilities between study participants with and without MCI in order to explore the relationship between cognitive and language abilities, and to identify a possible indicator for the early detection of MCI and dementia. We recruited 22 people aged 74 to 86 years (mean: 78.32 years; standard deviation: 3.36). The participants were requested to write and talk about one of the happiest events in their lives. Based on HDS-R scores, we divided the participants into 2 groups: the MCI Group comprised 8 participants with a score of 26 or lower, while the Healthy Group comprised 14 participants with a score of 27 or higher. The transcriptions of both written and spoken samples for each participant were used in the measurement of NLP-based language ability scores. Our analysis showed no significant differences in writing abilities between the 2 groups in any of the language ability scores. However, analysis of the spoken narrative showed that the MCI Group had a significantly larger vocabulary size. In addition, analysis of a metric that signified the gap in content between the spoken and written narratives also revealed a larger vocabulary size in the MCI Group. Individuals with early-stage MCI may be engaging in behavior to conceal their deteriorating cognition, thereby leading to a temporary increase in their active spoken vocabulary. These results indicate the possible detection of early stages of reduced cognition before dementia onset through the analysis of spoken narratives.

Profiling Speech and Pausing in Amyotrophic Lateral Sclerosis (ALS) and Frontotemporal Dementia (FTD)

Objective

This study examines reading aloud in patients with amyotrophic lateral sclerosis (ALS) and those with frontotemporal dementia (FTD) in order to determine whether differences in patterns of speaking and pausing exist between patients with primary motor vs. primary cognitive-linguistic deficits, and in contrast to healthy controls.

Design

136 participants were included in the study: 33 controls, 85 patients with ALS, and 18 patients with either the behavioural variant of FTD (FTD-BV) or progressive nonfluent aphasia (FTD-PNFA). Participants with ALS were further divided into 4 non-overlapping subgroups—mild, respiratory, bulbar (with oral-motor deficit) and bulbar-respiratory—based on the presence and severity of motor bulbar or respiratory signs. All participants read a passage aloud. Custom-made software was used to perform speech and pause analyses, and this provided measures of speaking and articulatory rates, duration of speech, and number and duration of pauses. These measures were statistically compared in different subgroups of patients.

Results

The results revealed clear differences between patient groups and healthy controls on the passage reading task. A speech-based motor function measure (i.e., articulatory rate) was able to distinguish patients with bulbar ALS or FTD-PNFA from those with respiratory ALS or FTD-BV. Distinguishing the disordered groups proved challenging based on the pausing measures.

Conclusions and Relevance

This study demonstrated the use of speech measures in the identification of those with an oral-motor deficit, and showed the usefulness of performing a relatively simple reading test to assess speech versus pause behaviors across the ALS—FTD disease continuum. The findings also suggest that motor speech assessment should be performed as part of the diagnostic workup for patients with FTD.

Understanding the Relationship between Social Cognition and Word Difficulty. A Language Based Analysis of Individuals with Autism Spectrum Disorder

BACKGROUND

Few quantitative studies have been conducted on the relationship between society and its languages. Individuals with autistic spectrum disorder (ASD) are known to experience social hardships, and a wide range of clinical information about their quality of life has been provided through numerous narrative analyses. However, the narratives of ASD patients have thus far been examined mainly through qualitative approaches.

OBJECTIVES

In this study, we analyzed adults with ASD to quantitatively examine the relationship between language abilities and ASD severity scores.

METHODS

We generated phonetic transcriptions of speeches by 16 ASD adults at an ASD workshop, and divided the participants into 2 groups according to their Social Responsiveness Scale(TM), 2nd Edition (SRS(TM)-2) scores (where higher scores represent more severe ASD): Group A comprised high-scoring ASD adults (SRS(TM)-2 score: ≥ 76) and Group B comprised low- and intermediate-scoring ASD adults (SRS(TM)-2 score: < 76). Using natural language processing (NLP)-based analytical methods, the narratives were converted into numerical data according to four language ability indicators, and the relationships between the language ability scores and ASD severity scores were compared.

RESULTS AND DISCUSSION

Group A showed a marginally negative correlation with the level of Japanese word difficulty (p < .10), while the "social cognition" subscale of the SRS(TM)-2 score showed a significantly negative correlation (p < .05) with word difficulty. When comparing only male participants, Group A demonstrated a significantly lower correlation with word difficulty level than Group B (p < .10).

CONCLUSION

Social communication was found to be strongly associated with the level of word difficulty in speech. The clinical applications of these findings may be available in the near future, and there is a need for further detailed study on language metrics designed for ASD adults.

Speech Interaction with Personal Assistive Robots Supporting Aging at Home for Individuals with Alzheimer’s Disease

Increases in the prevalence of dementia and Alzheimer’s disease (AD) are a growing challenge in many nations where healthcare infrastructures are ill-prepared for the upcoming demand for personal caregiving. To help individuals with AD live at home for longer, we are developing a mobile robot, called ED, intended to assist with activities of daily living through visual monitoring and verbal prompts in cases of difficulty. In a series of experiments, we study speech-based interactions between ED and each of 10 older adults with AD as the latter complete daily tasks in a simulated home environment. Traditional automatic speech recognition is evaluated in this environment, along with rates of verbal behaviors that indicate confusion or trouble with the conversation. Analysis reveals that speech recognition remains a challenge in this setup, especially during household tasks with individuals with AD. Across the verbal behaviors that indicate confusion, older adults with AD are very likely to simply ignore the robot, which accounts for over 40% of all such behaviors when interacting with the robot. This work provides a baseline assessment of the types of technical and communicative challenges that will need to be overcome for robots to be used effectively in the home for speech-based assistance with daily living.

Quantification of Speech Disfluency as a Marker of Medication-Induced Cognitive Impairment: An Application of Computerized Speech Analysis in Neuropharmacology

We present the results of a study investigating the use of speech and language characteristics extracted from spontaneous spoken discourse to assess changes in cognitive function. Specifically, we investigated the use of automatic speech recognition technology to characterize spontaneous speech disfluency induced by topiramate, an anti-epileptic medication with language-related side-effects. We audio recorded spontaneous speech samples from 20 participants during several picture description tasks and analyzed the recordings automatically and manually to extract a range of spoken fluency measurements including speech discontinuities (e.g., filled pauses, false starts, and repetitions), silent pause duration, speaking rate and vowel lengthening. Our results indicate that some of these paralinguistic speech characteristics are a) sensitive to the effects of topiramate, b) are associated with topiramate concentrations in the blood, and c) complement standard neuropsychological tests typically used to investigate cognitive effects of medications. This work demonstrates the use of computational linguistic tools to assess cognitive effects in a more sensitive, objective and reproducible manner than is currently available with standard tests.

The effect of topiramate plasma concentration on linguistic behavior, verbal recall and working memory

This is the first study of the effect of topiramate on linguistic behavior and verbal recall using a computational linguistics system for automated language and speech analysis to detect and quantify drug-induced changes in speech recorded during discourse-level tasks. Healthy volunteers were administered a single, 100-mg oral dose of topiramate in two double-blind, randomized, placebo-controlled, crossover studies. Subjects' topiramate plasma levels ranged from 0.23 to 2.81 μg/mL. We found a significant association between topiramate levels and impairment on measures of verbal fluency elicited during a picture description task, correct number of words recalled on a paragraph recall test, and reaction time recorded during a working memory task. Using the tools of clinical pharmacology and computational linguistics, we elucidated the relationship between the determinants of a drug's disposition as reflected in plasma concentrations and their impact on cognitive functioning as reflected in spoken language discourse.

Effects of age and dementia on temporal cycles in spontaneous speech fluency

Spontaneous speech of healthy adults consists of alternating periods of fluent and hesitant segments, forming temporal cycles in speech fluency. The regularity of these cycles may be related to the functioning of brain networks during speech planning and execution. This paper investigates the theoretical link between human cognitive functioning and temporal cycles in speech production using a quantitative time series analysis to characterize the regularity and frequency of temporal cycles in adults with differing levels and etiology of cognitive decline. We compare spontaneous speech of adults without a neurological diagnosis, both older and younger, to that of adults with frontotemporal lobar degeneration (FTLD). Two measures of temporal cycle frequency (mean and mode) calculated from the power spectrum of speech fluency represented as a time series were found to be associated with subjects' age, regardless of diagnosis of dementia. Two measures of periodicity (g-statistic and rhythmicity-index), as well as mean frequency, differentiated between adults with and without dementia. Our study confirms the presence of regular temporal cycles in spontaneous speech and suggests that temporal cycle characteristics are affected in different ways by declines in cognitive functioning due to dementia and aging.