000264110 001__ 264110
000264110 005__ 20190812204758.0
000264110 037__ $$aCONF
000264110 245__ $$aLearning voice source related information for depression detection
000264110 260__ $$c2019
000264110 269__ $$a2019
000264110 336__ $$aConference Papers
000264110 520__ $$aDuring depression neurophysiological changes can occur, which may affect laryngeal control i.e. behaviour of the vocal folds. Characterising these changes in a precise manner from speech signals is a non trivial task, as this typically involves reliable separation of the voice source information from them. In this paper, by exploiting the abilities of CNNs to learn task-relevant information from the input raw signals, we investigate several methods to model voice source related information for depression detection. Specifically, we investigate modelling of low pass filtered speech signals, linear prediction residual signals, homomorphically filtered voice source signals and zero frequency filtered signals to learn voice source related information for depression detection. Our investigations show that subsegmental level modelling of linear prediction residual signals or zero frequency filtered signals leads to systems better than the state-of-the-art low level descriptor based systems and deep learning based systems modelling the vocal tract system information.
000264110 6531_ $$aConvolutional Neural Networks
000264110 6531_ $$adepression detection
000264110 6531_ $$aglottal source signals.
000264110 6531_ $$azero-frequency filtering
000264110 700__ $$aDubagunta, S. Pavankumar
000264110 700__ $$aVlasenko, Bogdan
000264110 700__ $$aMagimai.-Doss, Mathew
000264110 7112_ $$aProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
000264110 8564_ $$zRelated documents$$xPUBLIC$$uhttp://publications.idiap.ch/downloads/papers/2019/Dubagunta_ICASSP-2_2019.pdf
000264110 909C0 $$xU10381$$pLIDIAP$$mfranck.formaz@epfl.ch$$0252189$$zMarselli, Béatrice
000264110 909CO $$qGLOBAL_SET$$pconf$$pSTI$$ooai:infoscience.epfl.ch:264110
000264110 970__ $$aDubagunta_ICASSP-2_2019/IDIAP
000264110 980__ $$aCONF