Name
Abstract | ||
|---|---|---|
The performance of an automatic speech recognition system heavily depends on the used feature set. Quality of speech recognition features is estimated by classification error, but then the recognition experiments must be performed, including both front-end and back-end implementations. We propose a method for features quality estimation that does not require recognition experiments and accelerate automatic speech recognition system development. The key component of our method is usage of metrics right after front-end features computation. The experimental results show that our method is suitable for recognition systems with back-end Euclidean space classifiers. |
Year | Venue | Keywords |
|---|---|---|
2013 | Informatica, Lith. Acad. Sci. | classes separability,quality of speech recognition features,speech recognition |
Field | DocType | Volume |
Signature recognition,Computer science,Feature (machine learning),Speaker recognition,Artificial intelligence,Computation,3D single-object recognition,Pattern recognition,Intelligent character recognition,Word error rate,Speech recognition,Machine learning,Acoustic model | Journal | 24 |
Issue | ISSN | Citations |
3 | 0868-4952 | 1 |
PageRank | References | Authors |
0.36 | 17 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rasa Lileikyte | 1 | 8 | 1.65 |
| Laimutis Telksnys | 2 | 31 | 5.83 |