Mood disorder identification using deep bottleneck features of elicited speech

Kun Yi Huang, Chung Hsien Wu, Ming Hsiang Su, Chia Hui Chou

研究成果: Conference contribution

4 引文 斯高帕斯(Scopus)

摘要

In the diagnosis of mental health disorder, a large portion of the Bipolar Disorder (BD) patients is likely to be misdiagnosed as Unipolar Depression (UD) on initial presentation. As speech is the most natural way to express emotion, this work focuses on tracking emotion profile of elicited speech for short-term mood disorder identification. In this work, the Deep Scattering Spectrum (DSS) and Low Level Descriptors (LLDs) of the elicited speech signals are extracted as the speech features. The hierarchical spectral clustering (HSC) algorithm is employed to adapt the emotion database to the mood disorder database to alleviate the data bias problem. The denoising autoencoder is then used to extract the bottleneck features of DSS and LLDs for better representation. Based on the bottleneck features, a long short term memory (LSTM) is applied to generate the time-varying emotion profile sequence. Finally, given the emotion profile sequence, the HMM-based identification and verification model is used to determine mood disorder. This work collected the elicited emotional speech data from 15 BDs, 15 UDs and 15 healthy controls for system training and evaluation. Five-fold cross validation was employed for evaluation. Experimental results show that the system using the bottleneck feature achieved an identification accuracy of 73.33%, improving by 8.89%, compared to that without bottleneck features. Furthermore, the system with verification mechanism, improving by 4.44%, outperformed that without verification.

原文English
主出版物標題Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1648-1652
頁數5
ISBN(電子)9781538615423
DOIs
出版狀態Published - 2017 7月 2
事件9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, Malaysia
持續時間: 2017 12月 122017 12月 15

出版系列

名字Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
2018-February

Other

Other9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
國家/地區Malaysia
城市Kuala Lumpur
期間17-12-1217-12-15

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 人機介面
  • 資訊系統
  • 訊號處理

指紋

深入研究「Mood disorder identification using deep bottleneck features of elicited speech」主題。共同形成了獨特的指紋。

引用此