Semantic similarity for detecting recognition errors in automatic speech transcripts
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
A methodology of error detection: improving speech recognition in radiology
A methodology of error detection: improving speech recognition in radiology
An investigation of linguistic information for speech recognition error detection
An investigation of linguistic information for speech recognition error detection
A novel voting scheme for ROVER using automatic error detection
AIS'12 Proceedings of the Third international conference on Autonomous and Intelligent Systems
Hi-index | 0.00 |
Speech recognition technology has been around for several decades now, and a considerable amount of applications have been developed around this technology. However, the current state of the art of speech recognition systems still generate errors in the recognizer's output. Techniques to automatically detect and even correct speech transcription errors have emerged. Due to the complexity of the problem, these error detection approaches have failed to ensure both a high recall and a precision ratio. The goal of this paper is to present an approach that combines several error detection techniques to ensure a better classification rate. Experimental results have proven that such an approach can indeed improve on the current state of the art of automatic error detection in speech transcription.