2012 Fiscal Year Final Research Report
Learning of Phoneme Sequence and Indicated Category from Spoken Utterances
| Project/Area Number |
23700200
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Nagoya Institute of Technology |
|---|
Principal Investigator |
TAGUCHI Ryo 名古屋工業大学, 工学研究科, 助教 (70508415)
|
|---|
| Project Period (FY) |
2011 – 2012
|
| Keywords | 音声情報処理 / 言語獲得 / シンボルグラウンディング |
|---|
| Research Abstract |
This report proposes a method for unsupervised learning of phoneme sequences of words and the categories indicated by the words from pairs of spoken utterances and feature vectors, which are gotten through human-robot interaction in the real-world, without any priori linguistic knowledge other than a phoneme acoustic model. Domestic robots must be able to learn phoneme sequences of unknown words and them meanings through human-robot interaction. In previous works, when users teach novel words to robots, they have to use isolated words or fixed phrases. However, in our method, robots can learn novel words from user's free utterances.
|
