Summary of the paper
| Title | Comparison of Spectral Properties of Read, Prepared and Casual Speech in French |
|---|---|
| Authors | Jean-Luc Rouas, Mayumi Beppu and Martine Adda-Decker |
| Abstract | In this paper, we investigate the acoustic properties of phonemes in threespeaking styles: read speech, prepared speech and spontaneous speech. Our aimis to better understand why speech recognition systems still fails to achievegood performances on spontaneous speech. This work follows the work of Nakamura et al. on Japanese speaking styles, withthe difference that we here focus on French. Using Nakamura's method, we useclassical speech recognition features, MFCC, and try to represent the effectsof the speaking styles on the spectral space. Two measurements are defined inorder to represent the spectral space reduction and the spectral varianceextension. Experiments are then carried on to investigate if indeed we findsome differences between the three speaking styles using these measurements. Wefinally compare our results to those obtained by Nakamura on Japanese to see ifthe same phenomenon appears. We happen to find some cues, and it also seemsthat phone duration also plays an important role regarding spectral reduction,especially for spontaneous speech. |
| Language | Other |
| Topics | Speech Recognition/Understanding, Discourse annotation, representation and processing, Other |
Full paper  |
Comparison of Spectral Properties of Read, Prepared and Casual Speech in French |
| Bibtex | @InProceedings{ROUAS10.704, author = {Jean-Luc Rouas, Mayumi Beppu and Martine Adda-Decker}, title = {Comparison of Spectral Properties of Read, Prepared and Casual Speech in French}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |