%Aigaion2 BibTeX export from Idiap Publications %Wednesday 04 December 2024 11:16:27 PM @TECHREPORT{Janbakhshi_Idiap-RR-08-2021, author = {Janbakhshi, Parvaneh and Kodrasi, Ina}, projects = {Idiap, MOSPEEDI}, month = {7}, title = {Supervised Speech Representation Learning for Parkinson's Disease Classification}, type = {Idiap-RR}, number = {Idiap-RR-08-2021}, year = {2021}, institution = {Idiap}, note = {accepted in ITG Conference on Speech Communication}, abstract = {Recently proposed automatic pathological speech classification techniques use unsupervised auto-encoders to obtain a high-level abstract representation of speech. Since these representations are learned based on reconstructing the input, there is no guarantee that they are robust to pathology-unrelated cues such as speaker identity information. Further, these representations are not necessarily discriminative for pathology detection. In this paper, we exploit supervised auto-encoders to extract robust and discriminative speech representations for Parkinson's disease classification. To reduce the influence of speaker variabilities unrelated to pathology, we propose to obtain speaker identity-invariant representations by adversarial training of an auto-encoder and a speaker identification task. To obtain a discriminative representation, we propose to jointly train an auto-encoder and a pathological speech classifier. Experimental results on a Spanish database show that the proposed supervised representation learning methods yield more robust and discriminative representations for automatically classifying Parkinson's disease speech, outperforming the baseline unsupervised representation learning system.}, pdf = {https://publications.idiap.ch/attachments/reports/2021/Janbakhshi_Idiap-RR-08-2021.pdf} }