The mu + system for corpus based speech research

J. Harrington, S. Cassidy, J. Fletcher, A. McVeigh

Research output: Contribution to journalArticleResearchpeer-review

Abstract

mu+ is a system for corpus based speech research that can be used to retrieve and analyse segments and their associated signal files from a large speech corpus. The segments can occur at many different levels (acoustic-phonetic, phonemic, intonational, prosodic), while the signal files can include the acoustic speech waveform, analysis parameters derived from the speech waveform (e.g. formant frequencies), and various articulatory measurements (e.g. kinematic parameters from lip and jaw movement). Most combinations of segment types, together with their boundary times and the speech signal files with which they are associated, can be retrieved hierarchically (all phonemes that occur in certain words), sequentially (all phonemes that occur in a particular triphone) or hierarchically and sequentially (e.g. all phonemes that occur in content words which are preceded by an intonational phrase of a particular type). The segments and their associated signal files that are retrieved from the speech database can be analysed subsequently using a wide range of statistical primitives and digital-signal-processing routines. The system has been developed to provide a common environment for experimentation in numerous facets of corpus based speech and language research including: articulatory and acoustic phonetics, prosodic analysis, speech technology research, and linguistic corpus development.

LanguageEnglish
Pages305-331
Number of pages27
JournalComputer Speech and Language
Volume7
Issue number4
DOIs
Publication statusPublished - Oct 1993

Fingerprint

Speech analysis
Acoustics
Waveform
Speech Analysis
Waveform analysis
Speech Signal
Facet
Experimentation
Signal Processing
Corpus
Speech
Digital signal processing
Kinematics
Linguistics
Range of data

Cite this

Harrington, J. ; Cassidy, S. ; Fletcher, J. ; McVeigh, A. / The mu + system for corpus based speech research. In: Computer Speech and Language. 1993 ; Vol. 7, No. 4. pp. 305-331.
@article{27ecdc3b2a954e7e976718f93cd16292,
title = "The mu + system for corpus based speech research",
abstract = "mu+ is a system for corpus based speech research that can be used to retrieve and analyse segments and their associated signal files from a large speech corpus. The segments can occur at many different levels (acoustic-phonetic, phonemic, intonational, prosodic), while the signal files can include the acoustic speech waveform, analysis parameters derived from the speech waveform (e.g. formant frequencies), and various articulatory measurements (e.g. kinematic parameters from lip and jaw movement). Most combinations of segment types, together with their boundary times and the speech signal files with which they are associated, can be retrieved hierarchically (all phonemes that occur in certain words), sequentially (all phonemes that occur in a particular triphone) or hierarchically and sequentially (e.g. all phonemes that occur in content words which are preceded by an intonational phrase of a particular type). The segments and their associated signal files that are retrieved from the speech database can be analysed subsequently using a wide range of statistical primitives and digital-signal-processing routines. The system has been developed to provide a common environment for experimentation in numerous facets of corpus based speech and language research including: articulatory and acoustic phonetics, prosodic analysis, speech technology research, and linguistic corpus development.",
author = "J. Harrington and S. Cassidy and J. Fletcher and A. McVeigh",
year = "1993",
month = "10",
doi = "10.1006/csla.1993.1017",
language = "English",
volume = "7",
pages = "305--331",
journal = "Computer Speech and Language",
issn = "0885-2308",
publisher = "Academic Press Inc.",
number = "4",

}

The mu + system for corpus based speech research. / Harrington, J.; Cassidy, S.; Fletcher, J.; McVeigh, A.

In: Computer Speech and Language, Vol. 7, No. 4, 10.1993, p. 305-331.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - The mu + system for corpus based speech research

AU - Harrington, J.

AU - Cassidy, S.

AU - Fletcher, J.

AU - McVeigh, A.

PY - 1993/10

Y1 - 1993/10

N2 - mu+ is a system for corpus based speech research that can be used to retrieve and analyse segments and their associated signal files from a large speech corpus. The segments can occur at many different levels (acoustic-phonetic, phonemic, intonational, prosodic), while the signal files can include the acoustic speech waveform, analysis parameters derived from the speech waveform (e.g. formant frequencies), and various articulatory measurements (e.g. kinematic parameters from lip and jaw movement). Most combinations of segment types, together with their boundary times and the speech signal files with which they are associated, can be retrieved hierarchically (all phonemes that occur in certain words), sequentially (all phonemes that occur in a particular triphone) or hierarchically and sequentially (e.g. all phonemes that occur in content words which are preceded by an intonational phrase of a particular type). The segments and their associated signal files that are retrieved from the speech database can be analysed subsequently using a wide range of statistical primitives and digital-signal-processing routines. The system has been developed to provide a common environment for experimentation in numerous facets of corpus based speech and language research including: articulatory and acoustic phonetics, prosodic analysis, speech technology research, and linguistic corpus development.

AB - mu+ is a system for corpus based speech research that can be used to retrieve and analyse segments and their associated signal files from a large speech corpus. The segments can occur at many different levels (acoustic-phonetic, phonemic, intonational, prosodic), while the signal files can include the acoustic speech waveform, analysis parameters derived from the speech waveform (e.g. formant frequencies), and various articulatory measurements (e.g. kinematic parameters from lip and jaw movement). Most combinations of segment types, together with their boundary times and the speech signal files with which they are associated, can be retrieved hierarchically (all phonemes that occur in certain words), sequentially (all phonemes that occur in a particular triphone) or hierarchically and sequentially (e.g. all phonemes that occur in content words which are preceded by an intonational phrase of a particular type). The segments and their associated signal files that are retrieved from the speech database can be analysed subsequently using a wide range of statistical primitives and digital-signal-processing routines. The system has been developed to provide a common environment for experimentation in numerous facets of corpus based speech and language research including: articulatory and acoustic phonetics, prosodic analysis, speech technology research, and linguistic corpus development.

UR - http://www.scopus.com/inward/record.url?scp=0027685296&partnerID=8YFLogxK

U2 - 10.1006/csla.1993.1017

DO - 10.1006/csla.1993.1017

M3 - Article

VL - 7

SP - 305

EP - 331

JO - Computer Speech and Language

T2 - Computer Speech and Language

JF - Computer Speech and Language

SN - 0885-2308

IS - 4

ER -