Automatic Measurement of Positive and Negative Voice Onset Time

Katharine Henry; Morgan Sonderegger; J. Keshet

Automatic Measurement of Positive and Negative Voice Onset Time

Katharine Henry, Morgan Sonderegger, J. Keshet

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Previous work on automatic VOT measurement has focused on positive-valued VOT. However, in many languages VOT can be either positive or negative (“prevoiced”). We present a discriminative algorithm that simultaneously decides whether a stop is prevoiced and measures its VOT. The algorithm operates on feature functions designed to locate the burst and voicing onsets in the positive and negative VOT cases. Tested on a database of positive- and negative-VOT voiced stops, the algorithm predicts prevoicing with >90% accuracy, and gives good agreement between automatic and manual measurements

Original language	American English
Title of host publication	INTERSPEECH
State	Published - 2012

Bibliographical note

Place of conference:USA

Cite this

@inproceedings{b2451d82fbc64f39909702e36d334d27,

title = "Automatic Measurement of Positive and Negative Voice Onset Time",

abstract = "Previous work on automatic VOT measurement has focused on positive-valued VOT. However, in many languages VOT can be either positive or negative (“prevoiced”). We present a discriminative algorithm that simultaneously decides whether a stop is prevoiced and measures its VOT. The algorithm operates on feature functions designed to locate the burst and voicing onsets in the positive and negative VOT cases. Tested on a database of positive- and negative-VOT voiced stops, the algorithm predicts prevoicing with >90% accuracy, and gives good agreement between automatic and manual measurements",

author = "Katharine Henry and Morgan Sonderegger and J. Keshet",

note = "Place of conference:USA",

year = "2012",

language = "American English",

booktitle = "INTERSPEECH",

}

TY - GEN

T1 - Automatic Measurement of Positive and Negative Voice Onset Time

AU - Henry, Katharine

AU - Sonderegger, Morgan

AU - Keshet, J.

N1 - Place of conference:USA

PY - 2012

Y1 - 2012

N2 - Previous work on automatic VOT measurement has focused on positive-valued VOT. However, in many languages VOT can be either positive or negative (“prevoiced”). We present a discriminative algorithm that simultaneously decides whether a stop is prevoiced and measures its VOT. The algorithm operates on feature functions designed to locate the burst and voicing onsets in the positive and negative VOT cases. Tested on a database of positive- and negative-VOT voiced stops, the algorithm predicts prevoicing with >90% accuracy, and gives good agreement between automatic and manual measurements

AB - Previous work on automatic VOT measurement has focused on positive-valued VOT. However, in many languages VOT can be either positive or negative (“prevoiced”). We present a discriminative algorithm that simultaneously decides whether a stop is prevoiced and measures its VOT. The algorithm operates on feature functions designed to locate the burst and voicing onsets in the positive and negative VOT cases. Tested on a database of positive- and negative-VOT voiced stops, the algorithm predicts prevoicing with >90% accuracy, and gives good agreement between automatic and manual measurements

UR - https://scholar.google.co.il/scholar?q=Automatic+Measurement+of+Positive+and+Negative+Voice+Onset+Time&btnG=&hl=en&as_sdt=0%2C5

M3 - Conference contribution

BT - INTERSPEECH

ER -

Automatic Measurement of Positive and Negative Voice Onset Time

Abstract

Bibliographical note

Other files and links

Fingerprint

Cite this