Mild cognitive impairment (MCI) has been recognized as a possible precursor to Alzheimer’s disease (AD). Recent research focusing on connected speech has uncovered various features strongly correlated with MCI due to AD and related dementias. Despite these advancements, the impact of early cognitive decline on articulatory precision has not been thoroughly investigated.
Objective
This study introduced the phoneme log-likelihood ratio (PLLR) to assess the articulatory precision of speakers across different cognitive status levels and compared its effectiveness to existing well-studied acoustic features.
Methods
The study utilized speech recordings from a picture description task, which included data from 324 cognitively unimpaired participants with low amyloid-β burden (CU, Aβ()), 47 cognitively unimpaired participants with high amyloid-β burden (CU, Aβ()), 69 participants with MCI, and 20 participants with dementia. Nine acoustic features were extracted from the speech recordings, covering three categories: speech fluency, speech pace, and articulatory precision. Welch’s -test and Hedge’s were adopted to assess their discriminative ability.
Results
A reduction in speech fluency and pace was observed among participants in the MCI and dementia groups. The PLLR shows large effect sizes in distinguishing between cognitively unimpaired participants with low Aβ burden and those diagnosed with MCI or dementia. Additionally, the test-retest reliability experiment indicated moderate repeatability of the features under study.
Conclusions
The study reveals PLLR as a sensitive indicator capable of detecting subtle articulatory variations across groups, while also providing further support for the association between reduced articulatory precision and early cognitive decline.
PetersenRC. Mild cognitive impairment as a diagnostic entity. J Intern Med2004; 256: 183–194.
2.
ChertkowHFeldmanHHJacovaC, et al. Definitions of dementia and predementia states in alzheimer’s disease and vascular cognitive impairment: Consensus from the Canadian conference on diagnosis of dementia. Alzheimers Res Ther2013; 5: 1–8.
HoopsSNazemSSiderowfA, et al. Validity of the moCA and MMSE in the detection of MCI and dementia in Parkinson disease. Neurology2009; 73: 1738–1745.
5.
DuffKPaulsenJMillsJ, et al. Mild cognitive impairment in prediagnosed Huntington disease. Neurology2010; 75: 500–507.
6.
DingHMandapatiAKarjadiC, et al. Association between acoustic features and neuropsychological test performance in the Framingham Heart Study: Observational study. J Med Internet Res2022; 24: e42886.
7.
van DyckCHSwansonCJAisenP, et al. Lecanemab in early Alzheimer’s disease. N Engl J Med2023; 388: 9–21.
8.
PulidoMLBHernándezJBABallesterMÁF, et al. Alzheimer’s disease and automatic speech analysis: a review. Expert Syst Appl2020; 150: 113213.
9.
LaskeCSohrabiHRFrostSM, et al. Innovative diagnostic tools for early detection of Alzheimer’s disease. Alzheimers Dement2015; 11: 561–578.
10.
HazanJWingMLiuKY, et al. Clinical utility of cerebrospinal fluid biomarkers in the evaluation of cognitive impairment: a systematic review and meta-analysis. J Neurol Neurosurg Psychiatry2023; 94: 113–120.
11.
BarthélemyNRSalvadóGSchindlerS, et al. Highly accurate blood test for Alzheimer’s disease comparable or superior to clinical CSF tests. Nat Med2024; 30: 1085–1095.
12.
JonaitisEMJanelidzeSCodyKA, et al. Plasma phosphorylated tau 217 in preclinical Alzheimer’s disease. Brain Commun2023; 5: fcad057.
13.
NasreddineZSPhillipsNABédirianV, et al. The Montreal Cognitive Assessment, MoCA: A brief screening tool for mild cognitive impairment. J Am Geriatr Soc2005; 53: 695–699.
14.
FolsteinMFFolsteinSEMcHughPR. “Mini-mental state”: a practical method for grading the cognitive state of patients for the clinician. J Psychiatr Res1975; 12: 189–198.
15.
WalterSDufouilCGrossAL, et al. Neuropsychological test performance and MRI markers of dementia risk: reducing education bias. Alzheimer Dis Assoc Disord2019; 33: 179.
16.
GreenP. The pervasive influence of effort on neuropsychological tests. Phys Med Rehabil Clin N Am2007; 18: 43–68.
17.
BarnettMDParsonsTDReynoldsBL, et al. Impact of rapport on neuropsychological test performance. Appl Neuropsychol Adult2018; 25: 258–265.
18.
ShirokyJSSchipperHMBergmanH, et al. Can you have dementia with an MMSE score of 30?Am J Alzheimers Dis Other Demen2007; 22: 406–415.
19.
KourtisLCRegeleOBWrightJM, et al. Digital biomarkers for Alzheimer’s disease: the mobile/wearable devices opportunity. NPJ Digit Med2019; 2: 9.
20.
DieffenderferJBrewerANoonanMA, et al. A wearable system for continuous monitoring and assessment of speech, gait, and cognitive decline for early diagnosis of ADRD. In: 45th Annu Int Conf IEEE Eng Med Biol Soc (EMBC). Piscataway, NJ: IEEE, pp. 1–6.
21.
BertiniFAlleviDLuteroG, et al. Automatic speech classifier for mild cognitive impairment and early dementia. ACM Trans Comput Healthc2021; 3: 1–11.
22.
RoarkBMitchellMHosomJP, et al. Spoken language derived measures for detecting mild cognitive impairment. IEEE Trans Audio Speech Lang Process2011; 19: 2081–2090.
23.
HoffmannINemethDDyeCD, et al. Temporal parameters of spontaneous speech in Alzheimer’s disease. Int J Speech-Lang Pathol2010; 12: 29–34.
24.
VinczeVGosztolyaGTóthL, et al. Detecting mild cognitive impairment by exploiting linguistic information from transcripts. In: Proc ACL (Vol. 2: Short Papers). Berlin, Germany: Association for Computational Linguistics, 2016, pp. 181–187.
25.
TóthLHoffmannIGosztolyaG, et al. A speech recognition-based solution for the automatic detection of mild cognitive impairment from spontaneous speech. Curr Alzheimer Res2018; 15: 130–138.
26.
AmbrosiniECaielliMMilisM, et al. Automatic speech analysis to early detect functional cognitive decline in elderly population. In: 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC). Piscataway, NJ: IEEE, pp.212–216.
27.
KönigASattASorinA, et al. Automatic speech analysis for the assessment of patients with predementia and Alzheimer’s disease. Alzheimers Dement (Amst)2015; 1: 112–124.
28.
ThemistocleousCEckerströmMKokkinakisD. Voice quality and speech fluency distinguish individuals with mild cognitive impairment from healthy controls. PLoS ONE2020; 15: e0236009.
29.
Martínez-SánchezFMeilánJJVera-FerrandizJA, et al. Speech rhythm alterations in Spanish-speaking individuals with Alzheimer’s disease. Aging Neuropsychol Cogn2017; 24: 418–434.
30.
LoizouCPPantzarisM. An automated speech analysis system for the detection of cognitive decline in elderly. Int J Speech Technol2023; 26: 337–353.
31.
MuellerKDHermannBMecollariJ, et al. Connected speech and language in mild cognitive impairment and Alzheimer’s disease: a review of picture description tasks. J Clin Exp Neuropsychol2018; 40: 917–939.
32.
MuellerKDKoscikRLHermannBP, et al. Declines in connected language are associated with very early mild cognitive impairment: results from the Wisconsin Registry for Alzheimer’s Prevention. Front Aging Neurosci2018; 9: 437.
33.
VerfaillieSCWittemanJSlotRE, et al. High amyloid burden is associated with fewer specific words during spontaneous speech in individuals with subjective cognitive decline. Neuropsychologia2019; 131: 184–192.
34.
MuellerKDVan HulleCAKoscikRL, et al. Amyloid beta associations with connected speech in cognitively unimpaired adults. Alzheimers Dement (Amst)2021; 13: e12203.
35.
ChapinKClarkeNGarrardP, et al. A finer-grained linguistic profile of Alzheimer’s disease and mild cognitive impairment. J Neurolinguistics2022; 63: 101069.
36.
JiaoYBerishaVLissJ, et al. Articulation entropy: an unsupervised measure of articulatory precision. IEEE Signal Process Lett2016; 24: 485–489.
37.
VoletiRLissJMBerishaV. A review of automated speech and language features for assessment of cognitive and thought disorders. IEEE J Sel Top Signal Process2019; 14: 282–298.
AmmarRBAyedYB. Language-related features for early detection of Alzheimer disease. Procedia Comput Sci2020; 176: 763–770.
40.
BorrieSAWynnCJBerishaV, et al. From speech acoustics to communicative participation in dysarthria: toward a causal framework. J Speech Lang Hear Res2022; 65: 405–418.
41.
WittSMYoungSJ. Phone-level pronunciation scoring and assessment for interactive language learning. Speech Commun2000; 30: 95–108.
42.
JohnsonSCKoscikRLJonaitisEM, et al. The Wisconsin Registry for Alzheimer’s Prevention: a review of findings and current directions. Alzheimers Dement (Amst)2018; 10: 130–142.
43.
Van HulleCJonaitisEMBetthauserTJ, et al. An examination of a novel multipanel of CSF biomarkers in the Alzheimer’s disease clinical and pathological continuum. Alzheimers Dement2021; 17: 431–445.
44.
Langhough KoscikRHermannBPAllisonS, et al. Validity evidence for the research category,“cognitively unimpaired–declining,” as a risk marker for mild cognitive impairment and Alzheimer’s disease. Front Aging Neurosci2021; 13: 688478.
45.
BlazelMMLazarKKVan HulleCA, et al. Factors associated with lumbar puncture participation in Alzheimer’s disease research. J Alzheimers Dis2020; 77: 1559–1567.
46.
GoodglassHKaplanEBarresiB. Boston Diagnostic Aphasia Examination – Third Edition. Philadelphia: Lippincott Williams & Wilkins, 2001.
47.
RacineAMKoscikRLNicholasCR, et al. Cerebrospinal fluid ratios with A42 predict preclinical brain -amyloid accumulation. Alzheimers Dement (Amst)2016; 2: 27–38.
48.
ReyA. L’examen psychologique dans les cas d’encephalopathie traumatique. Arch Psychol1941; 28: 286–340.
49.
Army Individual Test Battery. In: Manual of directions and scoring. Washington, DC: War Department, Adjutant General’s Office, 1944.
DuvallERobbinsAGrahamT, et al. Exploring filler words and their impact. Schwa Lang Linguist2014; 11: 35–49.
53.
BainMHuhJHanT, et al. WhisperX: Time-accurate speech transcription of long-form audio. In: Proc INTERSPEECH 2023. pp.4489–4493.
54.
HuWQianYSoongFK, et al. Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers. Speech Commun2015; 67: 154–166.
55.
SudhakaraSRamanathiMKYarraC, et al. An improved goodness of pronunciation (GoP) measure for pronunciation evaluation with DNN-HMM system considering HMM transition probabilities. In: Proc INTERSPEECH 2019. pp. 954–958.
56.
TuMGrabekALissJ, et al. Investigating the role of L1 in automatic pronunciation evaluation of L2 speech, 2018. arXiv:1807.01738.
57.
van AlbadaSJRobinsonPA. Transformation of arbitrary distributions to the normal distribution with application to EEG test–retest reliability. J Neurosci Methods2007; 161: 205–211.
58.
SmythGK. Polynomial approximation. In: Armitage P and Colton T (eds.) Encyclopedia of Biostatistics. London: Wiley, 2005, pp.3425–3429.
59.
StegmannGMHahnSLissJ, et al. Repeatability of commonly used speech and language features for clinical applications. Digit Biomark2020; 4: 109–122.
60.
FletcherJ. The prosody of speech: Timing and rhythm. In: Hardcastle WJ, Laver J and Gibbon FE (eds.) The Handbook of Phonetic Sciences. London: Wiley, 2010, pp.521–602.
61.
BónaJBaktiM. The effect of cognitive load on temporal and disfluency patterns of speech: evidence from consecutive interpreting and sight translation. Target2020; 32: 482–506.
62.
CeraMLOrtizKZBertolucciPHF, et al. Phonetic and phonological aspects of speech in Alzheimer’s disease. Aphasiology2018; 32: 88–102.
63.
Van Der MerweA. New perspectives on speech motor planning and programming in the context of the four-level model and its implications for understanding the pathophysiology underlying apraxia of speech and other motor speech disorders. Aphasiology2021; 35: 397–423.
64.
CeraMLOrtizKZBertolucciPHF, et al. Speech and phonological impairment across Alzheimer’s disease severity. J Commun Disord2023; 105: 106364.
65.
YoungCBSmithVKarjadiC, et al. Speech patterns during memory recall relates to early tau burden across adulthood. Alzheimers Dement2024; 20: 2552–2563.
66.
HajjarIOkaforMChoiJD, et al. Development of digital voice biomarkers and associations with cognition, cerebrospinal biomarkers, and neural representation in early Alzheimer’s disease. Alzheimers Dement (Amst)2023; 15: e12393.
67.
FleissJL. Design and analysis of clinical experiments. New York: John Wiley & Sons, 2011.
68.
LundbergSMLeeSI. A unified approach to interpreting model predictions. In: von LuxburgUGuyonIBengioSet al. (eds.) NIPS 2017, volume 30. Red Hook, NY: Curran Associates Inc., pp. 4768–4777.
