Detecting Signs of Dementia Using Word Vector Representations

Recent approaches to word vector representations, e.g., ‘w2vec’ and ‘GloVe’, have been shown to be powerful methods for capturing the semantics and syntax of words in a text. The approaches model the co-occurrences of words and recent successful applications on written text have shown how the vector representations and their interrelations represent the meaning or sentiment in the text. Most applications have targeted written language, however, in this paper, we investigate how these models port to the spoken language domain where the text is the result of (erroneous) automatic speech transcription. In particular, we are interested in the task of detecting signs of dementia in a person’s spoken language. This is motivated by the fact that early signs of dementia are known to affect a person’s ability to express meaning articulately for example when they engage in a conversation – something which is known to be cognitively very demanding. We analyse conversations designed to probe people’s short and long-term memory and propose three different methods for how word vectors may be used in a classification setup. We show that it is possible to identify dementia from the output of a speech recogniser despite a high occurrence of recognition errors.

[1]  H. Hamilton Conversations with an Alzheimer's Patient: An Interactional Sociolinguistic Study , 1994 .

[2]  Tanja Schultz,et al.  Manual and Automatic Transcriptions in Dementia Detection from Speech , 2017, INTERSPEECH.

[3]  Oded Shmueli,et al.  Using Word Embedding to Enable Semantic Queries in Relational Databases , 2017, DEEM@SIGMOD.

[4]  Karen Spärck Jones A statistical interpretation of term specificity and its application in retrieval , 2021, J. Documentation.

[5]  Gábor Gosztolya,et al.  A Speech Recognition-based Solution for the Automatic Detection of Mild Cognitive Impairment from Spontaneous Speech , 2018, Current Alzheimer research.

[6]  Kai Gao,et al.  Text Understanding with a Hybrid Neural Network Based Learning , 2017, ICPCSEE.

[7]  Carmen García-Mateo,et al.  Depression Detection Using Automatic Transcriptions of De-Identified Speech , 2017, INTERSPEECH.

[8]  Niklas Elmqvist,et al.  ConceptVector: Text Visual Analytics via Interactive Lexicon Building Using Word Embedding , 2018, IEEE Transactions on Visualization and Computer Graphics.

[9]  H. Brodaty,et al.  ALZHEIMER'S DISEASE INTERNATIONAL , 1997, International journal of geriatric psychiatry.

[10]  P. Drew,et al.  Towards diagnostic conversational profiles of patients presenting with dementia or functional memory disorders to memory clinics. , 2015, Patient education and counseling.

[11]  H. Christensen,et al.  Toward the Automation of Diagnostic Conversation Analysis in Patients with Memory Complaints. , 2017, Journal of Alzheimer's disease : JAD.

[12]  A. Kertesz,et al.  A study of language functioning in Alzheimer patients , 1982, Brain and Language.

[13]  Lei Chen,et al.  DNN Online with iVectors Acoustic Modeling and Doc2Vec Distributed Representations for Improving Automated Speech Scoring , 2016, INTERSPEECH.

[14]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[15]  Elmar Nöth,et al.  An N-Gram Based Approach to the Automatic Diagnosis of Alzheimer's Disease from Spoken Language , 2017, INTERSPEECH.

[16]  James R. Glass,et al.  Spoken language biomarkers for detecting cognitive impairment , 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

[17]  J. Becker,et al.  The natural history of Alzheimer's disease. Description of study cohort and accuracy of diagnosis. , 1994, Archives of neurology.

[18]  Daniel Povey,et al.  The Kaldi Speech Recognition Toolkit , 2011 .

[19]  Yaoru Sun,et al.  Sentiment Analysis of Movie Reviews Based on CNN-BLSTM , 2017, IFIP TC12 ICIS.

[20]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[21]  Heidi Christensen,et al.  Diagnosing People with Dementia Using Automatic Conversation Analysis , 2016, INTERSPEECH.

[22]  Heidi Christensen,et al.  An Avatar-Based System for Identifying Individuals Likely to Develop Dementia , 2017, INTERSPEECH.

[23]  Bhuvana Ramabhadran,et al.  Direct Acoustics-to-Word Models for English Conversational Speech Recognition , 2017, INTERSPEECH.

[24]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[25]  Zellig S. Harris,et al.  Distributional Structure , 1954 .

[26]  Kathleen C. Fraser,et al.  Linguistic Features Identify Alzheimer's Disease in Narrative Speech. , 2015, Journal of Alzheimer's disease : JAD.

[27]  Timothy Baldwin,et al.  An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation , 2016, Rep4NLP@ACL.

[28]  Markus Reuber,et al.  Can conversation analytic findings help with differential diagnosis in routine seizure clinic interactions? , 2016, Communication & medicine.

[29]  Alfred W. Kaszniak,et al.  Communication and Cognition in Normal Aging and Dementia , 1987 .

[30]  Christopher Potts,et al.  Learning Word Vectors for Sentiment Analysis , 2011, ACL.

[31]  Abhishek Verma,et al.  Deep CNN-LSTM with combined kernels from multiple branches for IMDb review sentiment analysis , 2017, 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON).

[32]  Gábor Gosztolya,et al.  Automatic detection of mild cognitive impairment from spontaneous speech using ASR , 2015, INTERSPEECH.

[33]  Tanja Schultz,et al.  Speech-Based Detection of Alzheimer's Disease in Conversational German , 2016, INTERSPEECH.

[34]  P. Drew,et al.  Conversational assessment in memory clinic encounters: interactional profiling for differentiating dementia from functional memory disorders , 2016, Aging & mental health.