Name
Abstract | ||
|---|---|---|
The Bayes decision theory is the foundation of the classical statistical pattern recognition approach, with the expected error as the performance objective. For most pattern recognition problems, the “error” is conventionally assumed to be binary, i.e., 0 or 1, equivalent to error counting, independent of the specifics of the error made by the system. The term “error rate” is thus long considered the prevalent system performance measure. This performance measure, nonetheless, may not be satisfactory in many practical applications. In automatic speech recognition, for example, it is well known that some errors are more detrimental (e.g., more likely to lead to misunderstanding of the spoken sentence) than others. In this paper, we propose an extended framework for the speech recognition problem with non-uniform classification/recognition error cost which can be controlled by the system designer. In particular, we address the issue of system model optimization when the cost of a recognition error is class dependent. We formulate the problem in the framework of the minimum classification error (MCE) method, after appropriate generalization to integrate the class-dependent error cost into one consistent objective function for optimization. We present a variety of training scenarios for automatic speech recognition under this extended framework. Experimental results for continuous speech recognition are provided to demonstrate the effectiveness of the new approach. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/TASL.2011.2165279 | IEEE Transactions on Audio, Speech & Language Processing |
Keywords | Field | DocType |
non-uniform error cost,minimum classification error cost (mcec),nonuniform classification error cost,non-uniform error criteria,speech recognition,minimum classification error,bayes methods,statistical analysis,mce method,statistical pattern recognition,error rate,nonuniform recognition error cost,recognition error,error counting,decision theory,expected error,recognition error cost,class-dependent error cost,classical statistical pattern recognition,extended framework,bayes decision theory,automatic speech recognition,system model optimization,cost function,pattern recognition,system design,measurement uncertainty,system performance,system modeling,objective function | Computer science,Speaker recognition,Feature (machine learning),Decision theory,Artificial intelligence,System model,Binary number,Pattern recognition,Word error rate,Measurement uncertainty,Speech recognition,Sentence,Machine learning | Journal |
Volume | Issue | ISSN |
20 | 3 | 1558-7916 |
Citations | PageRank | References |
4 | 0.38 | 14 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qiang Fu | 1 | 791 | 81.92 |
| Yong Zhao | 2 | 27 | 3.51 |
| Biing-Hwang Juang | 3 | 3388 | 699.72 |