Knowledge-driven speech features for detection of Korean-speaking children with autism spectrum disorder
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Detection of children with autism spectrum disorder (ASD) based on speech has relied on predefined feature sets due to their ease of use and the capabilities of speech analysis. However, clinical impressions may not be adequately captured due to the broad range and the large number of features included. This paper demonstrates that the knowledge-driven speech features (KDSFs) specifically tailored to the speech traits of ASD are more effective and efficient for detecting speech of ASD children from that of children with typical development (TD) than a predefined feature set, extended Geneva Minimalistic Acoustic Standard Parameter Set (eGeMAPS). The KDSFs encompass various speech characteristics related to frequency, voice quality, speech rate, and spectral features, that have been identified as corresponding to certain of their distinctive attributes of them. The speech dataset used for the experiments consists of 63 ASD children and 9 TD children. To alleviate the imbalance in the number of training utterances, a data augmentation technique was applied to TD children’s utterances. The support vector machine (SVM) classifier trained with the KDSFs achieved an accuracy of 91.25%, surpassing the 88.08% obtained using the predefined set. This result underscores the importance of incorporating domain knowledge in the development of speech technologies for individuals with disorders.
Abstract
Detection of children with autism spectrum disorder (ASD) based on speech has relied on predefined feature sets due to their ease of use and the capabilities of speech analysis. However, clinical impressions may not be adequately captured due to the broad range and the large number of features included. This paper demonstrates that the knowledge-driven speech features (KDSFs) specifically tailored to the speech traits of ASD are more effective and efficient for detecting speech of ASD children from that of children with typical development (TD) than a predefined feature set, extended Geneva Minimalistic Acoustic Standard Parameter Set (eGeMAPS). The KDSFs encompass various speech characteristics related to frequency, voice quality, speech rate, and spectral features, that have been identified as corresponding to certain of their distinctive attributes of them. The speech dataset used for the experiments consists of 63 ASD children and 9 TD children. To alleviate the imbalance in the number of training utterances, a data augmentation technique was applied to TD children’s utterances. The support vector machine (SVM) classifier trained with the KDSFs achieved an accuracy of 91.25%, surpassing the 88.08% obtained using the predefined set. This result underscores the importance of incorporating domain knowledge in the development of speech technologies for individuals with disorders.
참고문헌 (26)
- American Psychiatric Association, "Diagnostic and statistical manual of mental disorders" (2013), American Psychiatric Association
- Asgari, M., "Quantifying voice characteristics for detecting autism", Frontiers in Psychology, 12, pp.665096~ (2021)
- Barche, P., "Towards automatic assessment of voice disorders : A clinical approach", Proceedings of the INTERSPEECH 2020, pp.2537~2541 (2020)
- Beccaria, F., "Extraction and Classification of Acoustic Features from Italian Speaking Children with Autism Spectrum Disorders", Proceedings of the 2022 RaPID Workshop: Resources and ProcessIng of Linguistic, Para-Linguistic and Extralinguistic Data from People with Various Forms of Cognitive, Developmental Impairments-within the 13th Language Resources and Evaluation Conference, pp.2022[DOI]
- Benba, A., "Voiceprints analysis using MFCC and SVM for detecting patients with Parkinson’s disease", Proceedings of the 2015 International Conference on Electrical and Information Technologies (ICEIT), pp.300~304 (2015)
- Bone, D., "Spontaneous-speech acoustic-prosodic features of children with autism and the interacting psychologist", Proceedings of the INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association, pp.1043~1046 (2012)
- Bonneh, Y. S., "Abnormal speech spectrum and increased pitch variability in young autistic children", Frontiers in Human Neuroscience, 4, pp.237~ (2011)
- Cho, S., "Automatic detection of autism spectrum disorder in children using acoustic and text features from brief natural conversations", Proceedings of the INTERSPEECH 2019, pp.2513~2517 (2019)
- Diehl, J. J., "Acoustic differences in the imitation of prosodic patterns in children with autism spectrum disorders", Research in Autism Spectrum Disorders, 6(1), pp.123~134 (2012)
- Eyben, F., "The Geneva minimalistic acoustic parameter set(GeMAPS)for voice research and affective computing", IEEE Transactions on Affective Computing, 7(2), pp.190~202 (2016)
- Eyben, F., "Opensmile: The Munich versatile and fast open-source audio feature extractor", Proceedings of the 18th ACM International Conference on Multimedia, pp.1459~1462 (2010)
- Fusaroli, R., "Is voice a marker for autism spectrum disorder? A systematic review and meta-analysis", Autism Research, 10(3), pp.384~407 (2017)
- Haider, F., "An assessment of paralinguistic acoustic features for detection of Alzheimer’s dementia in spontaneous speech", IEEE Journal of Selected Topics in Signal Processing, 14(2), pp.272~281 (2020)
- Jadoul, Y., "Introducing Parselmouth : A Python interface to Praat", Journal of Phonetics, 71, pp.1~15 (2018)
- Assessment of phonology and articulation for children (APAC), "Kim, M. J.", Human Brain Research & Counseling, ~ (2007)
- Lee, J. H., "End-to-end model-based detection of infants with autism spectrum disorder using a pretrained model", Sensors, 23(1), pp.202~ (2023)
- Lord, C., "Autism diagnostic observation schedule" (2012), Western Psychological Corporation
- Lyakso, E., "Perception and acoustic features of speech of children with autism spectrum disorders", Proceedings of the 19th International Conference on Speech and Computer, pp.602~612 (2017)
- MacFarlane, H., "Combining voice and language features improves automated autism detection", Autism Research, 15(7), pp.1288~1300 (2022)
- McCann, J., "Prosody in autism spectrum disorders : A critical review", International Journal of Language & Communication Disorders, 38(4), pp.325~350 (2003)
- (2022)[URL]
- Mohanta, A., "Analysis and classification of speech sounds of children with autism spectrum disorder using acoustic features", Computer Speech & Language, 72, pp.101287~ (2022)
- Mohanta, A., "Acoustic features characterization of autism speech for automated detection and classification", Proceedings of the 2020 National Conference on Communications (NCC), pp.1~6 (2020)
- Park, D. S., "SpecAugment : A simple data augmentation method for automatic speech recognition", Proceedings of the INTERSPEECH 2019, pp.2613~2617 (2019)
- Pedregosa, F., "Scikit-learn : Machine learning in python", Journal of Machine Learning Research, 12(2011), pp.2825~2830 (2011)
- Yeo, E. J., "Automatic severity classification of Korean dysarthric speech using phoneme-level pronunciation features", Proceedings of the INTERSPEECH 2021, pp.4838~4842 (2021)