Integrating hidden Markov model and PRAAT: a toolbox for robust automatic speech transcription

A. Kabir; J. Barker; M. Giurgiu

doi:10.1117/12.872211

14 September 2010 Integrating hidden Markov model and PRAAT: a toolbox for robust automatic speech transcription

A. Kabir, J. Barker, M. Giurgiu

Proceedings Volume 7745, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2010; 774513 (2010) https://doi.org/10.1117/12.872211
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2010, 2010, Wilga, Poland

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.

Citation Download Citation

A. Kabir, J. Barker, and M. Giurgiu "Integrating hidden Markov model and PRAAT: a toolbox for robust automatic speech transcription", Proc. SPIE 7745, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2010, 774513 (14 September 2010); https://doi.org/10.1117/12.872211

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available