| ชื่อเรื่อง | : | A supervised two-channel learning method for hidden Markov model and application on lip reading |
| นักวิจัย | : | Foo, Say Wei , Dong, Liang |
| คำค้น | : | - |
| หน่วยงาน | : | Nanyang Technological University, Singapore |
| ผู้ร่วมงาน | : | - |
| ปีพิมพ์ | : | 2545 |
| อ้างอิง | : | Foo, S. W., & Dong, L. (2002). A supervised two-channel learning method for hidden Markov model and application on lip reading. IEEE International Conference on Advanced Learning Technologies. , http://hdl.handle.net/10220/4617 |
| ที่มา | : | - |
| ความเชี่ยวชาญ | : | - |
| ความสัมพันธ์ | : | - |
| ขอบเขตของเนื้อหา | : | - |
| บทคัดย่อ/คำอธิบาย | : | In this paper, a novel two-channel learning method for hidden Markov model (HMM) is proposed. This method is specially designed to train HMMs for fine recognition from similar observations. The prominent features of this method are 1.) the criterion function is based on the difference between training sequences, and 2.) a twochannel structure is adopted to maintain the validity of the HMM. This learning method has been applied on a viseme-level lip reading system. The result shows that the performance of the two channel approach is better than that of the maximum likelihood (ML) estimation. |
| บรรณานุกรม | : |
Foo, Say Wei , Dong, Liang . (2545). A supervised two-channel learning method for hidden Markov model and application on lip reading.
กรุงเทพมหานคร : Nanyang Technological University, Singapore. Foo, Say Wei , Dong, Liang . 2545. "A supervised two-channel learning method for hidden Markov model and application on lip reading".
กรุงเทพมหานคร : Nanyang Technological University, Singapore. Foo, Say Wei , Dong, Liang . "A supervised two-channel learning method for hidden Markov model and application on lip reading."
กรุงเทพมหานคร : Nanyang Technological University, Singapore, 2545. Print. Foo, Say Wei , Dong, Liang . A supervised two-channel learning method for hidden Markov model and application on lip reading. กรุงเทพมหานคร : Nanyang Technological University, Singapore; 2545.
|
ridm@nrct.go.th ระบบคลังข้อมูลงานวิจัยไทย รายการโปรดที่คุณเลือกไว้
