Phone-Attribute Posteriors to Evaluate the Speech of Cochlear Implant Users

Arias-Vergara, Tomás; Orozco-Arroyave, Juan Rafael; Cerňak, Miloš; Gollwitzer, Sandra; Schuster, Maria; Nöth, Elmar

doi:10.21437/interspeech.2019-2144

Cited by 4 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work has shown the suitability of phone-attribute features to evaluate articulation precision in people learning a second language [31] as well as to evaluate speech problems in patients affected by different medical conditions such as Parkinson's disease [32] and hearing loss [33]. In this work, phone-attribute features are computed using the CGRU described in Sect.…”

Section: Phone-attribute Featuresmentioning

confidence: 99%

Multi-channel spectrograms for speech processing applications using deep learning methods

Arias-Vergara

Klumpp

Vásquez-Correa

et al. 2020

Pattern Anal Applic

Self Cite

View full text Add to dashboard Cite

Time–frequency representations of the speech signals provide dynamic information about how the frequency component changes with time. In order to process this information, deep learning models with convolution layers can be used to obtain feature maps. In many speech processing applications, the time–frequency representations are obtained by applying the short-time Fourier transform and using single-channel input tensors to feed the models. However, this may limit the potential of convolutional networks to learn different representations of the audio signal. In this paper, we propose a methodology to combine three different time–frequency representations of the signals by computing continuous wavelet transform, Mel-spectrograms, and Gammatone spectrograms and combining then into 3D-channel spectrograms to analyze speech in two different applications: (1) automatic detection of speech deficits in cochlear implant users and (2) phoneme class recognition to extract phone-attribute features. For this, two different deep learning-based models are considered: convolutional neural networks and recurrent neural networks with convolution layers.

show abstract

Section: Phone-attribute Featuresmentioning

confidence: 99%

Multi-channel spectrograms for speech processing applications using deep learning methods

Arias-Vergara

Klumpp

Vásquez-Correa

et al. 2020

Pattern Anal Applic

Self Cite

View full text Add to dashboard Cite

show abstract

“…As described in Section 3.1, there exists a mismatch in age and perceptive BECD score between the AoS and dysarthria patients. As in [29], to determine whether the presented classification results of the proposed approach are biased by the age or perceptive BECD score of the patients (i.e., to determine whether the proposed feature sets characterize the age or perceptive BECD score of the patients instead of the MSD), we train Support Vector Regressors (SVR) with a Gaussian kernel on each of the three proposed feature sets. The regressors are trained to predict the age or the perceptive BECD score of the patients within a leave-one-speaker-out validation framework.…”

Section: Regression Analysesmentioning

confidence: 99%

Automatic Discrimination of Apraxia of Speech and Dysarthria Using a Minimalistic Set of Handcrafted Features

2020

View full text Add to dashboard Cite

To assist clinicians in the differential diagnosis and treatment of motor speech disorders, it is imperative to establish objective tools which can reliably characterize different subtypes of disorders such as apraxia of speech (AoS) and dysarthria. Objective tools in the context of speech disorders typically rely on thousands of acoustic features, which raises the risk of difficulties in the interpretation of the underlying mechanisms, overadaptation to training data, and weak generalization capabilities to test data. Seeking to use a small number of acoustic features and motivated by the clinical-perceptual signs used for the differential diagnosis of AoS and dysarthria, we propose to characterize differences between AoS and dysarthria using only six handcrafted acoustic features, with three features reflecting segmental distortions, two features reflecting loudness and hypernasality, and one feature reflecting syllabification. These three different sets of features are used to separately train three classifiers. At test time, the decisions of the three classifiers are combined through a simple majority voting scheme. Preliminary results show that the proposed approach achieves a discrimination accuracy of 90%, outperforming using state-of-the-art features such as openSMILE which yield a discrimination accuracy of 65%.

show abstract

Corpus Construction for Deaf Speakers and Analysis by Automatic Speech Recognition

Kobayashi,

Yasu

2023

2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

View full text Add to dashboard Cite

Phone-Attribute Posteriors to Evaluate the Speech of Cochlear Implant Users

Cited by 4 publications

References 16 publications

Multi-channel spectrograms for speech processing applications using deep learning methods

Multi-channel spectrograms for speech processing applications using deep learning methods

Automatic Discrimination of Apraxia of Speech and Dysarthria Using a Minimalistic Set of Handcrafted Features

Corpus Construction for Deaf Speakers and Analysis by Automatic Speech Recognition

Contact Info

Product

Resources

About