UDC 004.421.6, DOI: 10.2298/CSIS1001075T

A Dynamic Alignment Algorithm for Imperfect Speech and Transcript

Ye Tao1, 2, Xueqing Li1 and Bian Wu2

  1. Shandong University, Department of Computer Science and Technology
    Ji Nan, 250101, P. R. China
  2. Shanghai Qitai Internet Technology Co. Ltd.,
    Shanghai, 201203, P. R. China

Abstract

This paper presents a novel alignment approach for imperfect speech and the corresponding transcription. The algorithm gets started with multi-stage sentence boundary detection in audio, followed by a dynamic programming based search, to find the optimal alignment and detect the mismatches at sentence level. Experiments show promising performance, compared to the traditional forced alignment approach. The proposed algorithm has already been applied in preparing multimedia content for an online English training platform.

Key words

Text-Audio Alignment; Dynamic Programming

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS1001075T

Publication information

Volume 7, Issue 1 (February 2010)
Advances in Computer Animation and Digital Entertainment
Year of Publication: 2010
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Tao, Y., Li, X., Wu, B.: A Dynamic Alignment Algorithm for Imperfect Speech and Transcript. Computer Science and Information Systems, Vol. 7, No. 1. (2010), https://doi.org/10.2298/CSIS1001075T