Mark Tatham and Katherine Morton
- Published in print:
- 2003
- Published Online:
- September 2007
- ISBN:
- 9780199250677
- eISBN:
- 9780191719462
- Item type:
- chapter
- Publisher:
- Oxford University Press
- DOI:
- 10.1093/acprof:oso/9780199250677.003.0007
- Subject:
- Linguistics, Phonetics / Phonology
This chapter discusses the transfer of the parameters of natural expression to synthesis systems following current inadequate descriptions of natural speech, which highlights problems in deriving ...
More
This chapter discusses the transfer of the parameters of natural expression to synthesis systems following current inadequate descriptions of natural speech, which highlights problems in deriving adequate descriptions of expression and emotion. Voice quality, timing, and pitch contour all contribute — but quantifying these observations is currently incomplete and open to further research. Defining emotion in terms of acoustic correlates is discussed along with the variability in speech to which emotive content contributes. The non-uniqueness of acoustic correlates is emphasized, and the need for differentiating between high-level and low-level synthesis in the theoretical underpinning is discussed.Less
This chapter discusses the transfer of the parameters of natural expression to synthesis systems following current inadequate descriptions of natural speech, which highlights problems in deriving adequate descriptions of expression and emotion. Voice quality, timing, and pitch contour all contribute — but quantifying these observations is currently incomplete and open to further research. Defining emotion in terms of acoustic correlates is discussed along with the variability in speech to which emotive content contributes. The non-uniqueness of acoustic correlates is emphasized, and the need for differentiating between high-level and low-level synthesis in the theoretical underpinning is discussed.
Mark Tatham and Katherine Morton
- Published in print:
- 2003
- Published Online:
- September 2007
- ISBN:
- 9780199250677
- eISBN:
- 9780191719462
- Item type:
- chapter
- Publisher:
- Oxford University Press
- DOI:
- 10.1093/acprof:oso/9780199250677.003.0008
- Subject:
- Linguistics, Phonetics / Phonology
This chapter emphasizes the notion that human speech is listener-centred; speech is intended to be heard and understood. Adding expressive and emotive content provides the listener with information ...
More
This chapter emphasizes the notion that human speech is listener-centred; speech is intended to be heard and understood. Adding expressive and emotive content provides the listener with information about the speaker’s identity (gender, age, education, etc.), the speaker’s attitude and feelings toward the listener, and the nature of what is being said. Adding this to synthesis presents problems, including determining the most useful type of synthesizer, incorporating a proposed prosodic wrapper for speech, linking parameters of emotive content with acoustic parameters, and with underlying theory constructs such as category labels or parameters for driving the synthesizer. The relationship between high- and low-level synthesis, and how to incorporate a range of emotive content and voice quality are discussed.Less
This chapter emphasizes the notion that human speech is listener-centred; speech is intended to be heard and understood. Adding expressive and emotive content provides the listener with information about the speaker’s identity (gender, age, education, etc.), the speaker’s attitude and feelings toward the listener, and the nature of what is being said. Adding this to synthesis presents problems, including determining the most useful type of synthesizer, incorporating a proposed prosodic wrapper for speech, linking parameters of emotive content with acoustic parameters, and with underlying theory constructs such as category labels or parameters for driving the synthesizer. The relationship between high- and low-level synthesis, and how to incorporate a range of emotive content and voice quality are discussed.
