Chapter 4

A Large Margin Algorithm for Forced Alignment

Joseph Keshet

Joseph Keshet

IDIAP Research Institute, Martigny, Switzerland

Search for more papers by this author
Shai Shalev-Shwartz

Shai Shalev-Shwartz

Toyota Technological Institute at Chicago, Chicago, USA

Search for more papers by this author
Yoram Singer

Yoram Singer

Google Research, Google Inc., Mountain View, CA, USA

Search for more papers by this author
Dan Chazan

Dan Chazan

Department of Electrical Engineering, The Technion Institute of Technology, Haifa, Israel

Search for more papers by this author
First published: 14 January 2009

Portions reprinted, with permission, from Joseph Keshet, Shai Shalev-Shwartz, Yoram Singer and Dan Chazan, Large Margin Algorithm for Speech-to-Phoneme and Music-to-Score Alignment, IEEE Transactions on Audio, Speech and Language Processing, 15(8) 2373-2382, 2007. © 2008 IEEE.

Summary

This chapter contains sections titled:

  • Introduction

  • Problem Setting

  • Cost and Risk

  • A Large Margin Approach for Forced Alignment

  • An Iterative Algorithm

  • Efficient Evaluation of the Alignment Function

  • Base Alignment Functions

  • Experimental Results

  • Discussion

  • References

The full text of this article hosted at iucr.org is unavailable due to technical difficulties.