Abstract | ||
---|---|---|
•The effect of data augmentation technique has improved the performance of all applied classifiers.•The results on human transcripts show that, without feature engineering, the BLSTM outperform the CRF classifiers.•The results after added auxiliary features to support the CRFaux classifier allows performance improvements.•The results of CRFngram , CRFaux and BLSTM classifiers on ASR transcripts, scored against human transcription degrade in these three classifiers. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.csl.2019.101052 | Computer Speech & Language |
Keywords | Field | DocType |
Stuttering event detection,Speech disorder,CRF,BLSTM | Conditional random field,Transcription (linguistics),Sequence labeling,Stuttering,Computer science,Speech recognition,Feature engineering,Speech disorder,Classifier (linguistics) | Journal |
Volume | ISSN | Citations |
62 | 0885-2308 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sadeen Alharbi | 1 | 0 | 0.34 |
Madina Hasan | 2 | 13 | 5.35 |
Anthony J. Simons | 3 | 20 | 1.41 |
Shelagh Brumfitt | 4 | 0 | 0.34 |
Phil Green | 5 | 19 | 4.05 |