| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2014: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2013: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2012: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Outline of Final Research Achievements |
Many of the existing learner speech corpora include speech transcripts, but not audio files. In order to make the audio files publicly available, we need to consider how to prevent speakers' being identified by corpus users. In this research project, we investigated the possibility to apply the sound morphing technology for protection of speakers's anonymity and clarified how pitch and frequency of the original speech should be altered. We also investigated what kind of data retrieval system is needed for simultaneous analysis of transcripts and speeches.
|
