Abstract
Alzheimer’s disease (AD) is the most prevalent form of progressive degenerative dementia, which has a great impact on social economics throughout the world. In the vast majority of cases, AD patients are diagnosed by biochemical analysis, lumbar puncture and advanced imaging examination, which cannot play a preventive role in early stage of Alzheimer’s disease. Speech signals contain abundant personal information, especially AD patients always accompany with speech disorder, which provides a potential to utilize speech information to distinguish AD patients from healthy persons. The work presented in this paper aims to develop new approach for early detection of AD by noninvasive methods. We propose to make utilization of multimodal features with speech acoustic and linguistic features for the speech recognition of Alzheimer’s disease. Three different kinds of features, IS10_paraling features, deep acoustic using fine-tuned Wav2Vec2.0 model and deep linguistic features extracted using fine-tuned BERT, are adopted for AD classification by SVM classifier. By conducting experiments on two publicly available datasets of NCMMSC2021 and ADReSSo, the experimental results show that our model achieves state-of-the-art (SOTA) performance with satisfactory recognition effect. Our best-performing model obtains the accuracy of 89.1% and 84.0% in the long and short-audio of NCMMSC2021, and 83.7% in ADReSSo, which is promising for the early diagnosis and classification of AD patients.
Similar content being viewed by others
Data Availability
The data is not fully open access. The details can be found from http://www.ncmmsc2021.org/ and https://luzs.gitlab.io/adresso-2021/, respectively.
References
Mattson MP (2004) Pathways towards and away from alzheimer’s disease. Nature 430(7000):631–639
Xu L, Wu X, Chen K, Li Yao (2015) Multi-modality sparse representation-based classification for alzheimer’s disease and mild cognitive impairment. Comput Methods Prog Biomed 122(2):182–190
Mueller KD, Koscik RL, Hermann BP, Johnson SC, Turkstra LS (2018) Declines in connected language are associated with very early mild cognitive impairment: Results from the wisconsin registry for alzheimer’s prevention. Frontiers in Aging Neuroscience, p 9
Khelifa MOM, Elhadj YM, Abdellah Y, Belkasmi M (2017) Constructing accurate and robust hmm/gmm models for an arabic speech recognition system. Int J Speech Technol 20(4):937– 949
Wang D, Wang X, Lv S (2019) An overview of end-to-end automatic speech recognition. Symmetry 11(8):1018
Ying Y, Tu Y, Zhou H (2021) Unsupervised feature learning for speech emotion recognition based on autoencoder. Electronics 10(17):2086
Schuller B, Steidl S, Batliner A, Burkhardt F, Devillers L, Müller C, Narayanan S (2010) The interspeech 2010 paralinguistic challenge. In: Proc. INTERSPEECH 2010, Makuhari, Japan, pp 2794–2797
Eyben F, Scherer KR, Schuller BW, Sundberg J, André E, Busso C, Devillers LY, Epps J, Laukka P, Narayanan SS, Truong KP (2016) The geneva minimalistic acoustic parameter set (gemaps) for voice research and affective computing. IEEE Trans Affect Comput 7(2):190–202
Schuller B, Steidl S, Batliner A, Hirschberg J, Burgoon JK, Baird A, Elkins A, Zhang Y, Coutinho E, Evanini K et al (2016) The interspeech 2016 computational paralinguistics challenge: Deception, sincerity & native language. In: 17TH Annual conference of the international speech communication association (Interspeech 2016), vol 1-5, pp 2001–2005
Eyben F, Wöllmer M, Schuller B (2010) Opensmile: the munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM international conference on Multimedia, pp 1459–1462
Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert:, Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805
Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta:, A robustly optimized bert pretraining approach. arXiv:1907.11692
Baevski A, Zhou Y, Mohamed A, Auli M (2020) wav2vec 2.0: A framework for self-supervised learning of speech representations. Adv Neural Inf Process Syst 33:12449–12460
Chen S, Wang C, Chen Z, Wu Y, Liu S, Chen Z, Li J, Kanda N, Yoshioka T, Xiao X et al (2021) Wavlm:, Large-scale self-supervised pre-training for full stack speech processing. arXiv:2110.13900
Forbes-McKay KE, Venneri A (2005) Detecting subtle spontaneous language decline in early alzheimer’s disease with a picture description task. Neurol Sci 26(4):243–254
Mueller KD, Koscik RL, Hermann BP, Johnson SC, Turkstra LS (2018) Declines in connected language are associated with very early mild cognitive impairment: Results from the wisconsin registry for alzheimer’s prevention. Front Aging Neurosci 9:437
Haider F, De La Fuente S, Luz S (2019) An assessment of paralinguistic acoustic features for detection of alzheimer’s dementia in spontaneous speech. IEEE J Sel Top Signal Process 14(2):272–281
Nasreen S, Hough J, Purver M et al (2021) Detecting alzheimer’s disease using interactional and acoustic features from spontaneous speech Interspeech
Rohanian M, Hough J, Purver M (2021) Alzheimer’s dementia recognition using acoustic, lexical, disfluency and speech pause features robust to noisy inputs, arXiv:2106.15684
Yuan J, Bian Y, Cai X, Huang J, Ye Z, Church K (2020) Disfluencies and fine-tuning pre-trained language models for detection of alzheimer’s disease. In: INTERSPEECH, pp 2162–2166
Zhang C, Xue L (2021) Autoencoder with emotion embedding for speech emotion recognition. IEEE Access 9:51231–51241
Vasquez-Correa JC, Arias-Vergara T, Schuster M, Orozco-Arroyave JR, Nöth E (2020) Parallel representation learning for the classification of pathological speech: studies on parkinson’s disease and cleft lip and palate. Speech Comm 122:56–67
Padi S, Sadjadi SO, Sriram RD, Manocha D (2021) Improved speech emotion recognition using transfer learning and spectrogram augmentation. In: Proceedings of the 2021 international conference on multimodal interaction, pp 645–652
Chen L-W, Rudnicky A (2021) Exploring wav2vec 2.0 fine-tuning for improved speech emotion recognition. arXiv:2110.06309
Qin Y, Liu W, Peng Z, Ng S-I, Li J, Hu H, Lee T (2021) Exploiting pre-trained asr models for alzheimer’s disease recognition through spontaneous speech. arXiv:2110.01493
Balagopalan A, Eyre B, Rudzicz F, Novikova J (2020) To bert or not to bert:, comparing speech and language-based approaches for alzheimer’s disease detection. arXiv:2008.01551
Luz S, Haider F, De La Fuente S, Fromm D, MacWhinney B (2021) Detecting cognitive decline using speech only:, The adresso challenge. arXiv:2104.09356
Siriwardhana S, Reis Andrew, Weerasekera R, Nanayakkara S (2020) Jointly fine-tuning “bert-like” self supervised models to improve multimodal speech emotion recognition. arXiv:2008.06682
Syed MSS, Syed ZS, Lech M, Pirogova E (2020) Automated screening for alzheimer’s dementia through spontaneous speech. In: INTERSPEECH, pp 2222–2226
Chen J, Ye J, Tang F, Zhou J (2021) Automatic detection of alzheimer’s disease using spontaneous speech only. In: Proc. Interspeech, pp 3830–3834
Syed ZS, Syed MSS, Lech M, Pirogova E (2021) Tackling the adresso challenge 2021: the muet-rmit system for alzheimer’s dementia recognition from spontaneous speech. Proc Interspeech 2021:3815–3819
Qiao Y, Yin X, Wiechmann D, Kerz E (2021) Alzheimer’s disease detection from spontaneous speech through combining linguistic complexity and (dis) fluency features with pretrained language models arXiv:2106.08689
Syed Zafi Sherhan, Sidorov Kirill, Marshall David (2018) Automated screening for bipolar disorder from audio/visual modalities. In: Proceedings of the 2018 on Audio/visual emotion challenge and workshop, pp 39–45
Panayotov V, Chen G, Povey D, Khudanpur S (2015) Librispeech: an asr corpus based on public domain audio books. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 5206–5210. IEEE
Zhang T, Wu F, Katiyar A, Weinberger KQ, Artzi Y (2020) Revisiting few-sample bert fine-tuning. arXiv:2006.05987
Kim T, Kim HY (2019) Forecasting stock prices with a feature fusion lstm-cnn model using different representations of the same data. PloS one 14(2):e0212320
Liu G, He W, Jin B (2018) Feature fusion of speech emotion recognition based on deep learning. In: 2018 International conference on network infrastructure and digital content (IC-NIDC), pp 193–197, IEEE
Cui Y, Che W, Liu T, Qin B, Wang S, Hu G (2020) Revisiting pre-trained models for Chinese natural language processing. In: Proceedings of the 2020 Conference on empirical methods in natural language processing: Findings, pp 657–668, Online, November 2020. Association for Computational Linguistics
Pérez-Toro PA, Bayerl SP, Arias-Vergara T, Vásquez-Correa JC, Klumpp P, Schuster M, Nöth E, Orozco-Arroyave JR, Riedhammer K (2021) Influence of the interviewer on the automatic assessment of alzheimer’s disease in the context of the adresso challenge. In: Interspeech, pp 3785–3789
Wang N, Cao Y, Hao S, Shao Z, Subbalakshmi KP (2021) Modular multi-modal attention network for alzheimer’s disease detection using patient audio and language data. In: Interspeech, pp 3835–3839
Pappagari R, Cho J, Joshi S, Moro-Velázquez L, Zelasko P, Villalba J, Dehak N (2021) Automatic detection and assessment of alzheimer disease using speech and language technologies in low-resource scenarios. In: Interspeech, pp 3825–3829
Funding
This work is supported by Key Research and Development of Zhejiang Province of China under Grant 2021C03030 and National Key Research and Development Program of China under Grant 2019YFC0118202
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors have no conflicts of interest in this article.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Yangwei Ying and Tao Yang contributed equally to this work.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ying, Y., Yang, T. & Zhou, H. Multimodal fusion for alzheimer’s disease recognition. Appl Intell 53, 16029–16040 (2023). https://doi.org/10.1007/s10489-022-04255-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-04255-z