Multimodal I-vectors to Detect and Evaluate Parkinson's Disease

Garcia, N.; Vásquez-Correa, Juan Camilo; Orozco-Arroyave, Juan Rafael; Nöth, Elmar

doi:10.21437/interspeech.2018-2295

Cited by 10 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both classical machine learning and deep learning methods had been introduced in the classification of PD patients' speech. The Support Vector Machine (SVM) was widely selected and frequently performed well (Garcia et al, 2018;Arias-Vergara et al, 2018). Some studies also chose k nearest neighbor (KNN) and random forest (RF) to classify PD speech (Sakar et al, 2013;Zhang, 2017;Polat, 2019).…”

Section: Related Workmentioning

confidence: 99%

Parkinsonian Chinese Speech Analysis towards Automatic Classification of Parkinson's Disease

Fang¹,

Chen²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Speech disorders often occur at the early stage of Parkinson's disease (PD). The speech impairments could be indicators of the disorder for early diagnosis, while motor symptoms are not obvious. In this study, we constructed a new speech corpus of Mandarin Chinese and addressed classification of patients with PD. We implemented classical machine learning methods with ranking algorithms for feature selection, convolutional and recurrent deep networks, and an end to end system. Our classification accuracy significantly surpassed state-of-the-art studies. The result suggests that free talk has stronger classification power than standard speech tasks, which could help the design of future speech tasks for efficient early diagnosis of the disease. Based on existing classification methods and our natural speech study, the automatic detection of PD from daily conversation could be accessible to the majority of the clinical population.

show abstract

Section: Related Workmentioning

confidence: 99%

Parkinsonian Chinese Speech Analysis towards Automatic Classification of Parkinson's Disease

Fang¹,

Chen²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…For speech signals, such a space models the inter-and intra-speaker variability, in addition to channel effects. For this study we aim to capture changes in speech, handwriting, and gait due to the disease [21]. Ivectors have been considered previously to model handwriting [22] and gait data [23].…”

Section: User Models Based On I-vectorsmentioning

confidence: 99%

Comparison of User Models Based on GMM-UBM and I-Vectors for Speech, Handwriting, and Gait Assessment of Parkinson’s Disease Patients

Vásquez-Correa

Orozco-Arroyave

Nöth

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Parkinson's disease is a neurodegenerative disorder characterized by the presence of different motor impairments. Information from speech, handwriting, and gait signals have been considered to evaluate the neurological state of the patients. On the other hand, user models based on Gaussian mixture models -universal background models (GMM-UBM) and i-vectors are considered the state-of-the-art in biometric applications like speaker verification because they are able to model specific speaker traits. This study introduces the use of GMM-UBM and i-vectors to evaluate the neurological state of Parkinson's patients using information from speech, handwriting, and gait. The results show the importance of different feature sets from each type of signal in the assessment of the neurological state of the patients.

show abstract

“…Speaker embedding features, e.g. i-Vector [45,46], were used in speech assessment rather than ASR adaptation tasks.…”

Section: Introductionmentioning

confidence: 99%

Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition

Geng,

Liu,

et al. 2022

Preprint

View full text Add to dashboard Cite

Automatic recognition of disordered speech remains a highly challenging task to date. Sources of variability commonly found in normal speech including accent, age or gender, when further compounded with the underlying causes of speech impairment and varying severity levels, create large diversity among speakers. To this end, speaker adaptation techniques play a vital role in current speech recognition systems. Motivated by the spectro-temporal level differences between disordered and normal speech that systematically manifest in articulatory imprecision, decreased volume and clarity, slower speaking rates and increased dysfluencies, novel spectro-temporal subspace basis embedding deep features derived by SVD decomposition of speech spectrum are proposed to facilitate both accurate speech intelligibility assessment and auxiliary feature based speaker adaptation of state-of-the-art hybrid DNN and end-to-end disordered speech recognition systems. Experiments conducted on the UASpeech corpus suggest the proposed spectro-temporal deep feature adapted systems consistently outperformed baseline i-Vector adaptation by up to 2.63% absolute (8.6% relative) reduction in word error rate (WER) with or without data augmentation. Learning hidden unit contribution (LHUC) based speaker adaptation was further applied. The final speaker adapted system using the proposed spectral basis embedding features gave an overall WER of 25.6% on the UASpeech test set of 16 dysarthric speakers.

show abstract

Multimodal I-vectors to Detect and Evaluate Parkinson's Disease

Cited by 10 publications

References 20 publications

Parkinsonian Chinese Speech Analysis towards Automatic Classification of Parkinson's Disease

Parkinsonian Chinese Speech Analysis towards Automatic Classification of Parkinson's Disease

Comparison of User Models Based on GMM-UBM and I-Vectors for Speech, Handwriting, and Gait Assessment of Parkinson’s Disease Patients

Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition

Contact Info

Product

Resources

About