STAT: speech transcription analysis tool

Authors:
Stephen A. Kunath;Steven H. Weinberger
Affiliations:
3e4 George Mason University, Fairfax, VA;3e4 George Mason University, Fairfax, VA
Venue:
NAACL-Demonstrations '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Demonstration Session
Year:
2009

Citing 3
Cited 0

A new algorithm for the alignment of phonetic sequences

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Accent Classification in Speech

AUTOID '05 Proceedings of the Fourth IEEE Workshop on Automatic Identification Advanced Technologies
On using units trained on foreign data for improved multiple accent speech recognition

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Speech Transcription Analysis Tool (STAT) is an open source tool for aligning and comparing two phonetically transcribed texts of human speech. The output analysis is a parameterized set of phonological differences. These differences are based upon a selectable set of binary phonetic features such as [voice], [continuant], [high], etc. STAT was initially designed to provide sets of phonological speech patterns in the comparisons of various English accents found in the Speech Accent Archive http://accent.gmu.edu, but its scope and utility expand to matters of language assessment, phonetic training, forensic linguistics, and speech recognition.