%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 06:42:18 PM

@INPROCEEDINGS{Janbakhshi_ITG_2021,
         author = {Janbakhshi, Parvaneh and Kodrasi, Ina},
       projects = {Idiap, MOSPEEDI},
          month = sep,
          title = {Supervised Speech Representation Learning for Parkinson's Disease Classification},
      booktitle = {ITG Conference on Speech Communication},
           year = {2021},
       crossref = {Janbakhshi_Idiap-RR-08-2021},
            pdf = {https://publications.idiap.ch/attachments/papers/2021/Janbakhshi_ITG_2021.pdf}
}



crossreferenced publications: 
@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}
}