Multi-view representation learning via gcca for multimodal analysis of Parkinson's disease

Vásquez-Correa, Juan Camilo; Orozco-Arroyave, Juan Rafael; Arora, Raman; Nöth, Elmar; Dehak, Najim; Christensen, Heidi; Rudzicz, Frank; Bocklet, Tobias; Cerňak, Miloš; Chinaei, Hamidreza; Hannink, Julius; Nidadavolu, Phani Sankar; Yancheva, Maria; Vann, Alyssa; Vogler, Nikolai

doi:10.1109/icassp.2017.7952700

Cited by 30 publications

(31 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The baseline features include articulation and prosody-based features, which are concatenated to form a 724-dimensional feature vector per utterance (Orozco-Arroyave, 2016;Vasquez-Correa et al, 2017). The articulationbased features includes 86 descriptors such as the energy content distributed in 22 Bark bands in the transition from voiced to unvoiced segments (22 descriptors), and from unvoiced to voiced segments (22 descriptors) OrozcoArroyave et al (2016).…”

Section: Prediction Of Laryngeal Fda Scoresmentioning

confidence: 99%

“…All 50 PD speakers were considered in this evaluation. For the prediction task, we used the same Super Vector Regression as described by Vasquez-Correa et al (2017), using a leave-one-subjectout (LOSO) cross-validation. The performance is evaluated using the Spearman's correlation coefficient between the predicted scores and the real scores.…”

Section: Prediction Of Laryngeal Fda Scoresmentioning

confidence: 99%

See 1 more Smart Citation

Characterisation of voice quality of Parkinson’s disease using differential phonological posterior features

Cerňak

Orozco-Arroyave

Rudzicz

et al. 2017

Computer Speech & Language

View full text Add to dashboard Cite

Change in voice quality (VQ) is one of the first precursors of Parkinson's disease (PD). Specifically, impacted phonation and articulation causes the patient to have a breathy, husky-semiwhisper and hoarse voice.A goal of this paper is to characterize a VQ spectrum -the composition of non-modal phonations -of voice in PD. The paper relates non-modal healthy phonations: breathy, creaky, tense, falsetto and harsh, with disordered phonation in PD. First, statistics are learned to differentiate the modal and non-modal phonations. Statistics are computed using phonological posteriors, the probabilities of phonological features inferred from the speech signal using a deep learning approach. Second, statistics of disordered speech are learned from PD speech data comprising 50 patients and 50 healthy controls. Third, Euclidean distance is used to calculate similarity of non-modal and disordered statistics, and the inverse of the distances is used to obtain the composition of non-modal phonation in PD. Thus, pathological voice quality is characterised using healthy non-modal voice quality "base/eigenspace". The obtained results are interpreted as the voice of an average patient with PD and can be characterised by the voice quality spectrum composed of 30% breathy voice, 23% creaky voice, 20% tense voice, 15% falsetto voice and 12% harsh voice. In addition, the proposed features were applied for prediction * Corresponding author Email address: milos.cernak@idiap.ch (Milos Cernak) of the dysarthria level according to the Frenchay assessment score related to the larynx, and significant improvement is obtained for reading speech task. The proposed characterisation of VQ might also be applied to other kinds of pathological speech.

show abstract

Section: Prediction Of Laryngeal Fda Scoresmentioning

confidence: 99%

Section: Prediction Of Laryngeal Fda Scoresmentioning

confidence: 99%

Characterisation of voice quality of Parkinson’s disease using differential phonological posterior features

Cerňak

Orozco-Arroyave

Rudzicz

et al. 2017

Computer Speech & Language

View full text Add to dashboard Cite

show abstract

“…CCA/GCCA has an impressive array of applications in data mining and machine learning, including clustering [4], regression [5], outlier detection [6], natural language processing and word embedding [7], [8], [9], speech processing [10], heath care data analytics [11], genetics [12], [13], [14] and many C.I. Kanatsoulis more.…”

Section: Introductionmentioning

confidence: 99%

“…Very recently, Fu et al [23] proposed an efficient way to handle the SUMCOR problem, which is the first large-scale SUMCOR algorithm that scales up to truly large views. Fu et al [7] have also considered another popular formulation of GCCA, namely, the MAX-VAR GCCA [24], [10], [11] and proposed highly scalable algorithms for it in [7].…”

Section: Introductionmentioning

confidence: 99%

Structured SUMCOR Multiview Canonical Correlation Analysis for Large-Scale Data

Kanatsoulis

Sidiropoulos

et al. 2019

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

The sum-of-correlations (SUMCOR) formulation of generalized canonical correlation analysis (GCCA) seeks highly correlated low-dimensional representations of different views via maximizing pairwise latent similarity of the views. SUMCOR is considered arguably the most natural extension of classical two-view CCA to the multiview case, and thus has numerous applications in signal processing and data analytics. Recent work has proposed effective algorithms for handling the SUMCOR problem at very large scale. However, the existing scalable algorithms cannot incorporate structural regularization and prior information -which are critical for good performance in real-world applications. In this work, we propose a new computational framework for large-scale SUMCOR GCCA that can easily incorporate a suite of structural regularizers which are frequently used in data analytics. The updates of the proposed algorithm are lightweight and the memory complexity is also low. In addition, the proposed algorithm can be readily implemented in a parallel fashion. We show that the proposed algorithm converges to a Karush-Kuhn-Tucker (KKT) point of the regularized SUMCOR problem. Judiciously designed simulations and realdata experiments are employed to demonstrate the effectiveness of the proposed algorithm.

show abstract

“…There is still a lot of room for improvement, including a more objective scoring by PD speech specialists. Recent adoption of the Frenchay dysarthria Assessment (FDA) scale and the modified version (m-FDA) [7,8,9,10] have provided an alternative to the subjective UPDRS-III.1 score.…”

Section: Introductionmentioning

confidence: 99%

Feature Representation of Pathophysiology of Parkinsonian Dysarthria

Rueda¹,

Vásquez-Correa²,

Ríos-Urrego³

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

This paper focuses on selecting features that can best represent the pathophysiology of Parkinson's disease (PD) dysarthria. PD dysarthria has often been the subject of feature selection and classification experiments, but rarely have the selected features been attempted to be matched to the pathophysiology of PD dysarthria. PD dysarthria manifests through changes in control of a person's speech production muscles and affects respiration, articulation, resonance, and laryngeal properties, resulting in speech characteristics such as short phrases separated by pauses, reduced speed for non-repetitive syllables or supernormal speed of repetitive syllables, reduced resonance, irregular vowel generation, etc. Articulation, phonation, diadochokinesis (DDK) rhythm, and Empirical Mode Decomposition (EMD) features were extracted from the DDK and sustained /a/ recordings of the Spanish GITA Corpus. These recordings were captured from 50 healthy (HC) and 50 PD subjects. A two-stage filter-wrapper feature selection process was applied to reduce the number of features from 3,534 to 15. These 15 features mainly represent the instability of the voice and rhythm. SVM, Random Forest and Naive Bayes were used to test the discriminative power of the selected features. The results showed that these sustained /a/ and /pa-ta-ka/ stability features could successfully discriminate PD from HC with 70% accuracy.

show abstract

Multi-view representation learning via gcca for multimodal analysis of Parkinson's disease

Cited by 30 publications

References 15 publications

Characterisation of voice quality of Parkinson’s disease using differential phonological posterior features

Characterisation of voice quality of Parkinson’s disease using differential phonological posterior features

Structured SUMCOR Multiview Canonical Correlation Analysis for Large-Scale Data

Feature Representation of Pathophysiology of Parkinsonian Dysarthria

Contact Info

Product

Resources

About