DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Dae-Shik | - |
dc.contributor.advisor | 김대식 | - |
dc.contributor.author | Jeon, Jinwoo | - |
dc.date.accessioned | 2018-06-20T06:22:22Z | - |
dc.date.available | 2018-06-20T06:22:22Z | - |
dc.date.issued | 2017 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=675429&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/243321 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2017.2,[iii, 29 p. :] | - |
dc.description.abstract | Speaker identification is fundamentally important for the various purposes such as home device, surveillance or authorization. The main difficulty of speaker recognition is to improve the robust identification accuracy. In this paper, we present a multimodal method based on deep neural networks for speaker identification by using both face recognition and voice identification. Our proposed multimodal model shows more robust speaker identification performance. As a face recognition, we use a convolutional neural network, especially VGG Face descriptor networks. For voice identification, we use Gaussian Mixture Model based on i-vector. After feature extraction, feature vectors from each face and voice information are concatenated and trains multimodal deep neural network in order to get 1024-dimension multimodal embeddings. We validate the performance of our model by new dataset which consists of 281 TED videos. The multimodal DNN model depicts more reliable identification performance than single modality based identification methods like face recognition or speaker recognition. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Speaker Identification | - |
dc.subject | deep learning | - |
dc.subject | multimodal model | - |
dc.subject | i-vector | - |
dc.subject | convolutional neural network | - |
dc.subject | 화자 인식 | - |
dc.subject | 딥 러닝 | - |
dc.subject | 멀티모달 모델 | - |
dc.subject | i-벡터 | - |
dc.subject | 컨볼루젼 신경망 | - |
dc.title | Multimodal speaker identification using deep neural network | - |
dc.title.alternative | 깊은 신경망을 이용한 멀티모달 화자 인식 알고리즘 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 전진우 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.