E2E-DASR: End-to-end deep learning-based dysarthric automatic speech recognition
Dysarthria is a motor speech disability caused by weak muscles and organs involved in the
articulation process, thereby affecting the speech intelligibility of individuals. Because this …
articulation process, thereby affecting the speech intelligibility of individuals. Because this …
Experimental investigation on STFT phase representations for deep learning-based dysarthric speech detection
P Janbakhshi, I Kodrasi - ICASSP 2022-2022 IEEE …, 2022 - ieeexplore.ieee.org
Mainstream deep learning-based dysarthric speech detection approaches typically rely on
processing the magnitude spectrum of the short-time Fourier transform of input signals, while …
processing the magnitude spectrum of the short-time Fourier transform of input signals, while …
On using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches
Although the UA-Speech and TORGO databases of control and dysarthric speech are
invaluable resources made available to the research community with the objective of …
invaluable resources made available to the research community with the objective of …
A lightweight architecture for query-by-example keyword spotting on low-power iot devices
M Li - IEEE Transactions on Consumer Electronics, 2022 - ieeexplore.ieee.org
Keyword spotting (KWS) is a task to recognize a keyword or a particular command in a
continuous audio stream, which can be effectively applied to a voice trigger system that …
continuous audio stream, which can be effectively applied to a voice trigger system that …
Supervised speech representation learning for Parkinson's disease classification
P Janbakhshi, I Kodrasi - Speech Communication; 14th ITG …, 2021 - ieeexplore.ieee.org
Recently proposed automatic pathological speech classification techniques use
unsupervised auto-encoders to obtain a high-level abstract representation of speech. Since …
unsupervised auto-encoders to obtain a high-level abstract representation of speech. Since …
A depthwise separable CNN-based interpretable feature extraction network for automatic pathological voice detection
D Zhao, Z Qiu, Y Jiang, X Zhu, X Zhang… - … Signal Processing and …, 2024 - Elsevier
In recent years, deep learning methods in automatic pathological voice detection (APVD)
have gained satisfying results. However, most deep learning methods in APVD cannot …
have gained satisfying results. However, most deep learning methods in APVD cannot …
Automatic severity classification of dysarthric speech by using self-supervised model with multi-task learning
Automatic assessment of dysarthric speech is essential for sustained treatments and
rehabilitation. However, obtaining atypical speech is challenging, often leading to data …
rehabilitation. However, obtaining atypical speech is challenging, often leading to data …
Temporal envelope and fine structure cues for dysarthric speech detection using CNNs
I Kodrasi - IEEE Signal Processing Letters, 2021 - ieeexplore.ieee.org
Deep learning-based techniques for automatic dysarthric speech detection have recently
attracted interest in the research community. State-of-the-art techniques typically learn …
attracted interest in the research community. State-of-the-art techniques typically learn …
Speech intelligibility classifiers from 550k disordered speech samples
We developed dysarthric speech intelligibility classifiers on 551,176 disordered speech
samples contributed by a diverse set of 468 speakers, with a range of self-reported speaking …
samples contributed by a diverse set of 468 speakers, with a range of self-reported speaking …
Comparing supervised models and learned speech representations for classifying intelligibility of disordered speech on selected phrases
Automatic classification of disordered speech can provide an objective tool for identifying the
presence and severity of speech impairment. Classification approaches can also help …
presence and severity of speech impairment. Classification approaches can also help …