InterSpeech 2021

Identifying cognitive impairment using sentence representation vectors
(3 minutes introduction)

Bahman Mirheidari (University of Sheffield, UK), Yilin Pan (University of Sheffield, UK), Daniel Blackburn (University of Sheffield, UK), Ronan O’Malley (University of Sheffield, UK), Heidi Christensen (University of Sheffield, UK)
The widely used word vectors can be extended at the sentence level to perform a wide range of natural language processing (NLP) tasks. Recently the Bidirectional Encoder Representations from Transformers (BERT) language representation achieved state-of-the-art performance for these applications. The model is trained with punctuated and well-formed (writ-ten) text, however, the performance of the model drops significantly when the input text is the — erroneous and unpunctuated — output of automatic speech recognition (ASR). We use a sliding window and averaging approach for pre-processing text for BERT to extract features for classifying three diagnostic categories relating to cognitive impairment: neurodegenerative dis-order (ND), mild cognitive impairment (MCI), and healthy controls (HC). The in-house dataset contains the audio recordings of an intelligent virtual agent (IVA) who asks the participants several conversational questions prompts in addition to giving a picture description prompt. For the three-way classification, we achieve a 73.88% F-score (accuracy: 76.53%) using the pre-trained, uncased base BERT and for the two-way classifier (HC vs. ND) we achieve 89.80% (accuracy: 90%). We further improve these by using a prompt selection technique, reaching the F-scores of 79.98% (accuracy: 81.63%) and 93.56% (accuracy: 93.75%) respectively.