Speech Technologies: Language Variation

Simon King

doi:10.1016/B0-08-044854-2/01515-7

Speech Technologies: Language Variation

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

Abstract

Spoken language technologies, such as automatic speech recognition, must often deal with speech from many speakers and in a wide variety of situations. Variation in speech usually creates serious difficulties for such systems. This chapter looks at the many sources of variation in speech: within a single speaker, across speakers and languages, and in external factors.

Original language	English
Title of host publication	Encyclopedia of Language and Linguistics
Editors	Keith Brown
Publisher	Elsevier
Pages	56-61
Number of pages	6
Edition	2nd
ISBN (Print)	978-0-08-044854-1
DOIs	https://doi.org/10.1016/B0-08-044854-2/01515-7
Publication status	Published - Mar 2006

Keywords / Materials (for Non-textual outputs)

automatic speech recognition
co-articulation
speech signal processing
speech synthesis
text-to-speech synthesis
voice transformation

Access to Document

10.1016/B0-08-044854-2/01515-7

1515
© King, S. (2006). Speech technologies: Language variation. In K. Brown (Ed.), Encyclopedia of Language and Linguistics. (2nd ed., pp. 56-61). Elsevier. 10.1016/B0-08-044854-2/01515-7
Accepted author manuscript, 52.8 KB

http://www.sciencedirect.com/science/article/pii/B0080448542015157

Streamed models for automatic speech recognition (EPSRC Advanced Research Fellowship)
King, S.
EPSRC
1/01/05 → 31/12/09
Project: Research

Cite this

@inbook{c8ad08285a0d4173bf7b0e011636b504,

title = "Speech Technologies: Language Variation",

abstract = "Spoken language technologies, such as automatic speech recognition, must often deal with speech from many speakers and in a wide variety of situations. Variation in speech usually creates serious difficulties for such systems. This chapter looks at the many sources of variation in speech: within a single speaker, across speakers and languages, and in external factors.",

keywords = "automatic speech recognition, co-articulation, speech signal processing, speech synthesis, text-to-speech synthesis, voice transformation",

author = "Simon King",

year = "2006",

month = mar,

doi = "10.1016/B0-08-044854-2/01515-7",

language = "English",

isbn = "978-0-08-044854-1",

pages = "56--61",

editor = "Keith Brown",

booktitle = "Encyclopedia of Language and Linguistics",

publisher = "Elsevier",

address = "Netherlands",

edition = "2nd",

}

TY - CHAP

T1 - Speech Technologies: Language Variation

AU - King, Simon

PY - 2006/3

Y1 - 2006/3

N2 - Spoken language technologies, such as automatic speech recognition, must often deal with speech from many speakers and in a wide variety of situations. Variation in speech usually creates serious difficulties for such systems. This chapter looks at the many sources of variation in speech: within a single speaker, across speakers and languages, and in external factors.

AB - Spoken language technologies, such as automatic speech recognition, must often deal with speech from many speakers and in a wide variety of situations. Variation in speech usually creates serious difficulties for such systems. This chapter looks at the many sources of variation in speech: within a single speaker, across speakers and languages, and in external factors.

KW - automatic speech recognition

KW - co-articulation

KW - speech signal processing

KW - speech synthesis

KW - text-to-speech synthesis

KW - voice transformation

U2 - 10.1016/B0-08-044854-2/01515-7

DO - 10.1016/B0-08-044854-2/01515-7

M3 - Other chapter contribution

SN - 978-0-08-044854-1

SP - 56

EP - 61

BT - Encyclopedia of Language and Linguistics

A2 - Brown, Keith

PB - Elsevier

ER -

Speech Technologies: Language Variation

Abstract

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Projects

Streamed models for automatic speech recognition (EPSRC Advanced Research Fellowship)

Cite this