Automatic detection of Parkinsonian speech using wavelet scattering features.

• Tác giả: Paavo Alku, Mittapalle Kiran Reddy
• Ngôn ngữ: eng
• Ký hiệu phân loại: 025.347 *Pictures and materials for projection
• Thông tin xuất bản: United States : JASA express letters , 2025
• Bộ sưu tập: NCBI
• ID: 749887

Tóm tắt

In this paper, we study the automatic detection of Parkinson's disease (PD) from speech using features computed by a two-layer wavelet scattering network, which generates locally stable and translation-invariant features at each layer. The scattering features are encoded using Fisher vectors to obtain a single fixed-size feature vector per utterance. Support vector machine and feed-forward neural network classifiers are trained using the utterance-level features to perform the detection task (healthy vs PD). The results obtained with the PC-GITA database revealed that the proposed approach shows better results in comparison to the state-of-the-art techniques. The best classification accuracy of 87% was achieved with the proposed approach using speech from a text reading task.