GUBIAN, M., SCHUPPLER, B., van Doremalen, J.J.H.C., Sanders, E. & Boves, L. (2009) Novelty detection as a tool for automatic detection of orthographic transcription errors. Proceedings of the 13th International Conference on Speech and Computer SPECOM-2009, St. Petersburg, Russia
Making accurate orthographic transcriptions is very timeconsuming and in the case of extemporaneous speech of native and non-native speakers the task is extremely difficult. While previous research focused on evaluating phonemic transcriptions, the goal of our research is the automatic detection of transcription errors on the orthographic level, which degrade the quality of every following annotation level. Since it is hard to statistically characterize a bad transcription, we use a Novelty Detection approach to model accurate transcriptions only and use models of good transcriptions to reject all inputs that do not fit. A hand-segmented corpus of spontaneous speech is used to build models of correct transcriptions. The speech material is first subjected to a forced alignment; then two features, viz. duration and acoustic score from the ASR aligner, are extracted from each aligned phone and used for training and detection. A simple likelihood threshold method is employed on the alignment data in order to flag an utterance as incorrectly transcribed. We compare two different lexicons and discuss different issues with our approach to error detection.
