Spectro-Temporal Representation of Speech for Intelligibility Assessment of Dysarthria (Record no. 17797)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 01829caa a2200229 4500 |
| 022 ## - INTERNATIONAL STANDARD SERIAL NUMBER | |
| International Standard Serial Number | 1941-0484 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Chandrashekar, H. M. |
| 245 #0 - TITLE STATEMENT | |
| Title | Spectro-Temporal Representation of Speech for Intelligibility Assessment of Dysarthria |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Name of publisher, distributor, etc. | IEEE |
| Date of publication, distribution, etc. | 2020 |
| 270 ## - ADDRESS | |
| Address | Department of Clinical Sciences, All India Institute of Speech and Hearing, Mysore, India |
| 270 ## - ADDRESS | |
| Address | Department of Electronics and Communication Engineering, Siddaganga Institute of Technology, Tumkur, India |
| 270 ## - ADDRESS | |
| Address | Department of Electronics and Communication Engineering, Siddaganga Institute of Technology, Tumkur, India |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 390 - 399 |
| 490 ## - SERIES STATEMENT | |
| Volume/sequential designation | Volume 14 Issue 2 |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | 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. |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Sreedevi, N |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Veena Karjigi |
| 773 ## - HOST ITEM ENTRY | |
| Main entry heading | IEEE Journal of Selected Topics in Signal Processing |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | https://doi.org/10.1109/JSTSP.2019.2949912 |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | Faculty Publications |
| -- | FJAS |
No items available.