Share Email Print
cover

Proceedings Paper

Integrating hidden Markov model and PRAAT: a toolbox for robust automatic speech transcription
Author(s): A. Kabir; J. Barker; M. Giurgiu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

An automatic time-aligned phone transcription toolbox of English speech corpora has been developed. Especially the toolbox would be very useful to generate robust automatic transcription and able to produce phone level transcription using speaker independent models as well as speaker dependent models without manual intervention. The system is based on standard Hidden Markov Models (HMM) approach and it was successfully experimented over a large audiovisual speech corpus namely GRID corpus. One of the most powerful features of the toolbox is the increased flexibility in speech processing where the speech community would be able to import the automatic transcription generated by HMM Toolkit (HTK) into a popular transcription software, PRAAT, and vice-versa. The toolbox has been evaluated through statistical analysis on GRID data which shows that automatic transcription deviates by an average of 20 ms with respect to manual transcription.

Paper Details

Date Published: 15 September 2010
PDF: 6 pages
Proc. SPIE 7745, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2010, 774513 (15 September 2010); doi: 10.1117/12.872211
Show Author Affiliations
A. Kabir, Technical Univ. of Cluj-Napoca (Romania)
J. Barker, The Univ. of Sheffield (United Kingdom)
M. Giurgiu, Technical Univ. of Cluj-Napoca (Romania)


Published in SPIE Proceedings Vol. 7745:
Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2010
Ryszard S. Romaniuk, Editor(s)

© SPIE. Terms of Use
Back to Top