Manual Transcription of Conversational Speech at the Articulatory Feature Level

Karen Livescu, Ari Bezman, Nash M. Borges, Lisa Yung, Özgür Çetin, Joe Frankel, Simon King, Mathew Magimai-Doss, Xuemin Chi, Lisa LavoieICASSP 2007 · OpenReview

Abstract

We present an approach for the manual labeling of speech at the articulatory feature level, and a new set of labeled conversational speech collected using this approach. A detailed transcription, including overlapping or reduced gestures, is useful for studying the great pronunciation variability in conversational speech. It also facilitates the testing of feature classifiers, such as those used in articulatory approaches to automatic speech recognition. We describe an effort to transcribe a small set of utterances drawn from the Switchboard database using eight articulatory tiers. Two transcribers have labeled these utterances in a multi-pass strategy, allowing for correction of errors. We describe the data collection methods and analyze the data to determine how quickly and reliably this type of transcription can be done. Finally, we demonstrate one use of the new data set by testing a set of multilayer perceptron feature classifiers against both the manual labels and forced alignments.
BibTeX
@inproceedings{livescu2007manual,
  author = {Karen Livescu and Ari Bezman and Nash M. Borges and Lisa Yung and Özgür Çetin and Joe Frankel and Simon King and Mathew Magimai-Doss and Xuemin Chi and Lisa Lavoie},
  title = {{Manual Transcription of Conversational Speech at the Articulatory Feature Level}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2007},
  url = {https://openreview.net/forum?id=cshodb-qoUa},
}

Loading related content...

Figure