Phoneme segmentation of speech

Bartosz Ziolko; Suresh Manandhar; Richard C. Wilson

Phoneme segmentation of speech

Bartosz Ziolko, Suresh Manandhar, Richard C. Wilson

Computer Science

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

Abstract

In most approaches to speech recognition, the speech signals are segmented using constant-time segmentation, for example into 25 ms blocks. Constant segmentation risks losing information about the phonemes. Different sounds may be merged into single blocks and individual phonemes lost completely.

A more satisfactory approach is to attempt to segment the phoneme boundaries from the speech signals and use these boundaries to define blocks. The discrete wavelet transform (DWT) is interesting in the analysis of speech since it is easy to extract parameters which take into account the properties of the human hearing system. The analysis of the power in different frequency bands offers potential for distinguishing the start and end of phonemes. For many boundaries, there is no discernible drop in overall power, and at some frequencies, the power is broadly constant over the lifetime of the phoneme. However, many phonemes exhibit rapid changes in particular subbands which can be used to detect their start and endpoints.

In this paper we apply the DWT to speech signals and analyse the resulting power spectrum and its derivatives to locate candidates for the boundaries of phonemes in continuous speech. We compare the results with hand segmentation and constant segmentation over a number of words. The method proves effective for finding most phoneme boundaries.

Original language	English
Title of host publication	18th International Conference on Pattern Recognition, Vol 4, Proceedings
Editors	YY Tang, SP Wang, G Lorette, DS Yeung, H Yan
Place of Publication	LOS ALAMITOS
Publisher	IEEE Computer Society
Pages	282-285
Number of pages	4
ISBN (Print)	0-7695-2521-0
Publication status	Published - 2006
Event	18th International Conference on Pattern Recognition (ICPR 2006) - Hong Kong Duration: 20 Aug 2006 → 24 Aug 2006

Conference

Conference	18th International Conference on Pattern Recognition (ICPR 2006)
City	Hong Kong
Period	20/08/06 → 24/08/06

Keywords

RECOGNITION

Cite this

@inproceedings{2c7bb4cc9d374cc4b1d2334129d40f06,

title = "Phoneme segmentation of speech",

abstract = "In most approaches to speech recognition, the speech signals are segmented using constant-time segmentation, for example into 25 ms blocks. Constant segmentation risks losing information about the phonemes. Different sounds may be merged into single blocks and individual phonemes lost completely.A more satisfactory approach is to attempt to segment the phoneme boundaries from the speech signals and use these boundaries to define blocks. The discrete wavelet transform (DWT) is interesting in the analysis of speech since it is easy to extract parameters which take into account the properties of the human hearing system. The analysis of the power in different frequency bands offers potential for distinguishing the start and end of phonemes. For many boundaries, there is no discernible drop in overall power, and at some frequencies, the power is broadly constant over the lifetime of the phoneme. However, many phonemes exhibit rapid changes in particular subbands which can be used to detect their start and endpoints.In this paper we apply the DWT to speech signals and analyse the resulting power spectrum and its derivatives to locate candidates for the boundaries of phonemes in continuous speech. We compare the results with hand segmentation and constant segmentation over a number of words. The method proves effective for finding most phoneme boundaries.",

keywords = "RECOGNITION",

author = "Bartosz Ziolko and Suresh Manandhar and Wilson, {Richard C.}",

year = "2006",

language = "English",

isbn = "0-7695-2521-0",

pages = "282--285",

editor = "YY Tang and SP Wang and G Lorette and DS Yeung and H Yan",

booktitle = "18th International Conference on Pattern Recognition, Vol 4, Proceedings",

publisher = "IEEE Computer Society",

address = "United States",

note = "18th International Conference on Pattern Recognition (ICPR 2006) ; Conference date: 20-08-2006 Through 24-08-2006",

}

TY - GEN

T1 - Phoneme segmentation of speech

AU - Ziolko, Bartosz

AU - Manandhar, Suresh

AU - Wilson, Richard C.

PY - 2006

Y1 - 2006

N2 - In most approaches to speech recognition, the speech signals are segmented using constant-time segmentation, for example into 25 ms blocks. Constant segmentation risks losing information about the phonemes. Different sounds may be merged into single blocks and individual phonemes lost completely.A more satisfactory approach is to attempt to segment the phoneme boundaries from the speech signals and use these boundaries to define blocks. The discrete wavelet transform (DWT) is interesting in the analysis of speech since it is easy to extract parameters which take into account the properties of the human hearing system. The analysis of the power in different frequency bands offers potential for distinguishing the start and end of phonemes. For many boundaries, there is no discernible drop in overall power, and at some frequencies, the power is broadly constant over the lifetime of the phoneme. However, many phonemes exhibit rapid changes in particular subbands which can be used to detect their start and endpoints.In this paper we apply the DWT to speech signals and analyse the resulting power spectrum and its derivatives to locate candidates for the boundaries of phonemes in continuous speech. We compare the results with hand segmentation and constant segmentation over a number of words. The method proves effective for finding most phoneme boundaries.

AB - In most approaches to speech recognition, the speech signals are segmented using constant-time segmentation, for example into 25 ms blocks. Constant segmentation risks losing information about the phonemes. Different sounds may be merged into single blocks and individual phonemes lost completely.A more satisfactory approach is to attempt to segment the phoneme boundaries from the speech signals and use these boundaries to define blocks. The discrete wavelet transform (DWT) is interesting in the analysis of speech since it is easy to extract parameters which take into account the properties of the human hearing system. The analysis of the power in different frequency bands offers potential for distinguishing the start and end of phonemes. For many boundaries, there is no discernible drop in overall power, and at some frequencies, the power is broadly constant over the lifetime of the phoneme. However, many phonemes exhibit rapid changes in particular subbands which can be used to detect their start and endpoints.In this paper we apply the DWT to speech signals and analyse the resulting power spectrum and its derivatives to locate candidates for the boundaries of phonemes in continuous speech. We compare the results with hand segmentation and constant segmentation over a number of words. The method proves effective for finding most phoneme boundaries.

KW - RECOGNITION

M3 - Conference contribution

SN - 0-7695-2521-0

SP - 282

EP - 285

BT - 18th International Conference on Pattern Recognition, Vol 4, Proceedings

A2 - Tang, YY

A2 - Wang, SP

A2 - Lorette, G

A2 - Yeung, DS

A2 - Yan, H

PB - IEEE Computer Society

CY - LOS ALAMITOS

T2 - 18th International Conference on Pattern Recognition (ICPR 2006)

Y2 - 20 August 2006 through 24 August 2006

ER -