Spectro-Temporal Representation of Speech for Intelligibility Assessment of Dysarthria
| Autor: | H. M. Chandrashekar, N. Sreedevi, Veena Karjigi |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Artificial neural network
Computer science Speech recognition Feature extraction 020206 networking & telecommunications 02 engineering and technology Intelligibility (communication) Speech processing Convolutional neural network Dysarthria Signal Processing 0202 electrical engineering electronic engineering information engineering medicine Spectrogram Electrical and Electronic Engineering medicine.symptom Classifier (UML) |
| Zdroj: | IEEE Journal of Selected Topics in Signal Processing. 14:390-399 |
| ISSN: | 1941-0484 1932-4553 |
| DOI: | 10.1109/jstsp.2019.2949912 |
| Popis: | Recently, spectro-temporal representation of speech has been used in many fields of speech processing. Owing to this, we explore the use of spectro-temporal representation for speech intelligibility assessment especially for dysarthric speech. In this work, we investigate the use of spectro-temporal representations to evaluate intelligibility levels using artificial neural network (ANN) and convolutional neural network (CNN). Standard American English dysarthric databases namely Universal Access and TORGO are used for evaluation. Performance of CNN classifier is superior to ANN as it is an advanced classifier. Further, use of Time-Frequency CNN configuration proved to capture spectro-temporal variations together resulting in an improved performance compared to either Time-CNN or Frequency-CNN configurations which capture either temporal or spectral variations respectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|