Prosodic Processing

Jan van Santen, Taniya Mishra, Esther Klabbers

Research output: Chapter in Book/Report/Conference proceedingChapter

3 Citations (Scopus)

Abstract

Speech synthesis speechsynthesis systems have to generate natural-sounding speech output from text. One of the key aspects of speech is prosodic processing prosody, which must be both natural (i.e., sounding like a human) and meaningful (i.e., sounding like a human who understands the contents of the text). The computation of prosody from text can be divided into the computation of prosodic tags from text and the computation of acoustic speech features from these tags. This chapter focuses on the latter. It provides an overview of prosody in human-human communication, including the communicative functions of prosody and the acoustic correlates. Discussed next is a historical overview of the various methods that have been used for prosody generation in speech synthesis, as well as of current methods. Special attention is paid to prosody generation in unit selection synthesis methods, in which large corpora are searched for fragments of speech that match the phonemes and prosodic tags computed from text and that optimize various cost functions, and in which prosody is not modeled and speech not modified. We conclude the chapter by advocating hybrid approaches in which search capabilities of unit selection methods are combined with the speech modification methods from more-traditional approaches.

Original languageEnglish (US)
Title of host publicationSpringer Handbooks
PublisherSpringer
Pages471-488
Number of pages18
DOIs
StatePublished - Jan 1 2008

Publication series

NameSpringer Handbooks
ISSN (Print)2522-8692
ISSN (Electronic)2522-8706

Fingerprint

Processing
Speech synthesis
Acoustics
Cost functions
Communication

Keywords

  • Intonational Phrase
  • Pitch Accent
  • Pitch Contour
  • Speech Synthesis System
  • Unit Selection

ASJC Scopus subject areas

  • General

Cite this

van Santen, J., Mishra, T., & Klabbers, E. (2008). Prosodic Processing. In Springer Handbooks (pp. 471-488). (Springer Handbooks). Springer. https://doi.org/10.1007/978-3-540-49127-9_23

Prosodic Processing. / van Santen, Jan; Mishra, Taniya; Klabbers, Esther.

Springer Handbooks. Springer, 2008. p. 471-488 (Springer Handbooks).

Research output: Chapter in Book/Report/Conference proceedingChapter

van Santen, J, Mishra, T & Klabbers, E 2008, Prosodic Processing. in Springer Handbooks. Springer Handbooks, Springer, pp. 471-488. https://doi.org/10.1007/978-3-540-49127-9_23
van Santen J, Mishra T, Klabbers E. Prosodic Processing. In Springer Handbooks. Springer. 2008. p. 471-488. (Springer Handbooks). https://doi.org/10.1007/978-3-540-49127-9_23
van Santen, Jan ; Mishra, Taniya ; Klabbers, Esther. / Prosodic Processing. Springer Handbooks. Springer, 2008. pp. 471-488 (Springer Handbooks).
@inbook{3b9304e5e3b948cdb5f002112e68e833,
title = "Prosodic Processing",
abstract = "Speech synthesis speechsynthesis systems have to generate natural-sounding speech output from text. One of the key aspects of speech is prosodic processing prosody, which must be both natural (i.e., sounding like a human) and meaningful (i.e., sounding like a human who understands the contents of the text). The computation of prosody from text can be divided into the computation of prosodic tags from text and the computation of acoustic speech features from these tags. This chapter focuses on the latter. It provides an overview of prosody in human-human communication, including the communicative functions of prosody and the acoustic correlates. Discussed next is a historical overview of the various methods that have been used for prosody generation in speech synthesis, as well as of current methods. Special attention is paid to prosody generation in unit selection synthesis methods, in which large corpora are searched for fragments of speech that match the phonemes and prosodic tags computed from text and that optimize various cost functions, and in which prosody is not modeled and speech not modified. We conclude the chapter by advocating hybrid approaches in which search capabilities of unit selection methods are combined with the speech modification methods from more-traditional approaches.",
keywords = "Intonational Phrase, Pitch Accent, Pitch Contour, Speech Synthesis System, Unit Selection",
author = "{van Santen}, Jan and Taniya Mishra and Esther Klabbers",
year = "2008",
month = "1",
day = "1",
doi = "10.1007/978-3-540-49127-9_23",
language = "English (US)",
series = "Springer Handbooks",
publisher = "Springer",
pages = "471--488",
booktitle = "Springer Handbooks",

}

TY - CHAP

T1 - Prosodic Processing

AU - van Santen, Jan

AU - Mishra, Taniya

AU - Klabbers, Esther

PY - 2008/1/1

Y1 - 2008/1/1

N2 - Speech synthesis speechsynthesis systems have to generate natural-sounding speech output from text. One of the key aspects of speech is prosodic processing prosody, which must be both natural (i.e., sounding like a human) and meaningful (i.e., sounding like a human who understands the contents of the text). The computation of prosody from text can be divided into the computation of prosodic tags from text and the computation of acoustic speech features from these tags. This chapter focuses on the latter. It provides an overview of prosody in human-human communication, including the communicative functions of prosody and the acoustic correlates. Discussed next is a historical overview of the various methods that have been used for prosody generation in speech synthesis, as well as of current methods. Special attention is paid to prosody generation in unit selection synthesis methods, in which large corpora are searched for fragments of speech that match the phonemes and prosodic tags computed from text and that optimize various cost functions, and in which prosody is not modeled and speech not modified. We conclude the chapter by advocating hybrid approaches in which search capabilities of unit selection methods are combined with the speech modification methods from more-traditional approaches.

AB - Speech synthesis speechsynthesis systems have to generate natural-sounding speech output from text. One of the key aspects of speech is prosodic processing prosody, which must be both natural (i.e., sounding like a human) and meaningful (i.e., sounding like a human who understands the contents of the text). The computation of prosody from text can be divided into the computation of prosodic tags from text and the computation of acoustic speech features from these tags. This chapter focuses on the latter. It provides an overview of prosody in human-human communication, including the communicative functions of prosody and the acoustic correlates. Discussed next is a historical overview of the various methods that have been used for prosody generation in speech synthesis, as well as of current methods. Special attention is paid to prosody generation in unit selection synthesis methods, in which large corpora are searched for fragments of speech that match the phonemes and prosodic tags computed from text and that optimize various cost functions, and in which prosody is not modeled and speech not modified. We conclude the chapter by advocating hybrid approaches in which search capabilities of unit selection methods are combined with the speech modification methods from more-traditional approaches.

KW - Intonational Phrase

KW - Pitch Accent

KW - Pitch Contour

KW - Speech Synthesis System

KW - Unit Selection

UR - http://www.scopus.com/inward/record.url?scp=84868924957&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868924957&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-49127-9_23

DO - 10.1007/978-3-540-49127-9_23

M3 - Chapter

AN - SCOPUS:84868924957

T3 - Springer Handbooks

SP - 471

EP - 488

BT - Springer Handbooks

PB - Springer

ER -