Automatic Detection of Depression in Speech Using Ensemble Convolutional Neural Networks
| Autor: | Adrián Vázquez-Romero, Ascensión Gallardo-Antolín |
|---|---|
| Přispěvatelé: | Ministerio de Economía y Competitividad (España) |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
speech Ensemble averaging General Physics and Astronomy lcsh:Astrophysics 02 engineering and technology Convolutional neural network Article 03 medical and health sciences Depression detection Ensemble learning lcsh:QB460-466 convolutional neural networks 0202 electrical engineering electronic engineering information engineering Speech lcsh:Science 030304 developmental biology Telecomunicaciones 0303 health sciences business.industry Pattern recognition lcsh:QC1-999 Support vector machine ComputingMethodologies_PATTERNRECOGNITION depression detection ensemble learning lcsh:Q Convolutional neural networks 020201 artificial intelligence & image processing Artificial intelligence business Classifier (UML) lcsh:Physics |
| Zdroj: | e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid instname Entropy e-Archivo: Repositorio Institucional de la Universidad Carlos III de Madrid Universidad Carlos III de Madrid (UC3M) Volume 22 Issue 6 Entropy, Vol 22, Iss 688, p 688 (2020) |
| ISSN: | 1099-4300 |
| Popis: | This paper proposes a speech-based method for automatic depression classification. The system is based on ensemble learning for Convolutional Neural Networks (CNNs) and is evaluated using the data and the experimental protocol provided in the Depression Classification Sub-Challenge (DCC) at the 2016 Audio&ndash Visual Emotion Challenge (AVEC-2016). In the pre-processing phase, speech files are represented as a sequence of log-spectrograms and randomly sampled to balance positive and negative samples. For the classification task itself, first, a more suitable architecture for this task, based on One-Dimensional Convolutional Neural Networks, is built. Secondly, several of these CNN-based models are trained with different initializations and then the corresponding individual predictions are fused by using an Ensemble Averaging algorithm and combined per speaker to get an appropriate final decision. The proposed ensemble system achieves satisfactory results on the DCC at the AVEC-2016 in comparison with a reference system based on Support Vector Machines and hand-crafted features, with a CNN+LSTM-based system called DepAudionet, and with the case of a single CNN-based classifier. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |