TR-2006-04

Additional Cues for Mandarin Tone Recognition

Dinoj Surendran; Gina-Anne Levow. 25 May, 2006.
Communicated by Gina-Anne Levow.

Abstract

Most cues for Mandarin tone recognition involve pitch, overall intensity and duration. This paper investigates ten other possible cues, and finds one that results in modest, but significant, improvement in classification accuracy on a small speaker-independent corpus of Mandarin news broadcast speech. This cue consists of the energies in the sixteen non-overlapping bands of bandwidth 500Hz from 0 to 8kHz. Most of the improvement is in differentiating the neutral tone from the high, rising, and low tones.

Original Document

The original document is available in PDF (uploaded 25 May, 2006 by Gina-Anne Levow).

Additional Document Formats

The document is also available in Postscript (uploaded 25 May, 2006 by Gina-Anne Levow).

NOTE: The author warrants that these additional documents are identical with the originial to the extent permitted by the translation between the various formats. However, the webmaster has made no effort to verify this claim. If the authenticity of the document is an issue, please always refer to the "Original document." If you find significant alterations, please report to webmaster@cs.uchicago.edu.