Name
Title | ||
|---|---|---|
Assessing The Degree Of Nativeness And Parkinson'S Condition Using Gaussian Processes And Deep Rectifier Neural Networks |
Abstract | ||
|---|---|---|
The Interspeech 2015 Computational Paralinguistics Challenge includes two regression learning tasks, namely the Parkinson's Condition Sub-Challenge and the Degree of Nativeness Sub Challenge. We evaluated two state-of-the-art machine learning methods on the tasks, namely Deep Neural Networks (DNN) and Gaussian Processes Regression (GPR). We also experiented with various classifier combination and feature selection methods. For the Degree of Nativeness sub-challenge we obtained a far better Spearman correlation value than the one presented in the baseline paper. As regards the Parkinson's Condition Sub Challenge, we showed that both DNN and GPR are competitive with the baseline SVM, and that the results can be improved further by combining the classifiers. However, we obtained by far the best results when we applied a speaker clustering method to identify the files that belong to the same speaker. |
Year | Venue | Keywords |
|---|---|---|
2015 | 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5 | Computational Paralinguistics, Challenge, Parkinson's Condition, Degree of Nativeness, Deep Neural Networks, Gaussian Processes |
Field | DocType | Citations |
Regression,Feature selection,Pattern recognition,Computer science,Support vector machine,Speech recognition,Gaussian process,Artificial intelligence,Artificial neural network,Classifier (linguistics),Cluster analysis,Spearman's rank correlation coefficient | Conference | 2 |
PageRank | References | Authors |
0.37 | 10 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tamás Grósz | 1 | 24 | 6.10 |
| Róbert Busa-Fekete | 2 | 23 | 4.48 |
| Gábor Gosztolya | 3 | 75 | 21.66 |
| László Tóth | 4 | 169 | 30.52 |