Construction of criteria for annotation of utterance-units based on acoustic features
Project/Area Number |
24700109
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Media informatics/Database
|
Research Institution | National Institute for Japanese Language and Linguistics (2013) National Institute of Informatics (2012) |
Principal Investigator |
ISHIMOTO Yuichi 大学共同利用機関法人人間文化研究機構国立国語研究所, 研究情報資料センター, 特任助教 (50409786)
|
Project Period (FY) |
2012-04-01 – 2014-03-31
|
Project Status |
Completed (Fiscal Year 2013)
|
Budget Amount *help |
¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2013: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2012: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
Keywords | 韻律 / 自発発話 / 話者交替 / 発話末予測 / コーパス |
Research Abstract |
To construct subjective criteria for annotation of utterance-units related to turn-taking, I analyzed the prosodic behavior of spontaneous utterances. Furthermore, to clarify usefulness of prosodic features for a definition of the unit, I confirmed the influence on cognition of the end-of-utterance for hearers by perceptual experiments using utterances altered a part close to the end. In the results, the fundamental frequency (F0) range of the utterance was fixed to a certain width, and the F0s decline toward the end of the utterance in that range. The F0 declination is reset at the strong syntactic boundary in the utterance, and the final lowering occurs only at the end of the utterance. In addition, the conspicuous changes in the prosodic features occur mostly at the final accentual phrase with utterance-final elements. In the perceptual experiments, hearers can predict whether there is a following utterance-final element, and they feel that the end of the utterance arrives soon.
|
Report
(3 results)
Research Products
(24 results)