公告日期:
2018-12-03
公告單位:
公告分類:
公告標題:
系生組seminar演講公告(12/5)
公告內容:
 
 

演講人:中央研究院 資訊科技創新研究中心  曹昱博士
題目:Deep Learning Algorithms and Their Applications in Speech and Medical Signal Processing and Recognition
時間:107年12月5日(三) 下午3:00 -5:00
地點:中央大學電機系 E1-120教室
摘要:Pattern recognition and machine learning have become indispensable tools for managing big data from diverse sources such as image, text, speech, and medical data. Deep learning allows machines to learn high-level concepts from very low-level data. The hierarchical deep structure mimics human cognitive functions such as those involved in vision or hearing perception. In the first part of this talk, we will first present the background and some successful applications of deep learning algorithms. Next, we will introduce our achievements of speech signal processing and recognition tasks based on deep learning algorithms. We will also introduce our recent research focus on multi-modal speech enhancement and noise adaptive speech enhancement using domain adversarial training. Then we will introduce how to apply these derived algorithms on [assistive listening device (ALD), hearing aids (HAs), and cochlear implants (CIs)] to benefit the speech communication for hearing-impaired patients and subsequently enhance their quality of life. I will also present our recent progress of developing machine-learning-based assistive speaking devices. Oral cancer ranks in the top five of all cancers in Taiwan. To treat the oral cancer, surgical processes are often required to have parts of the patients’ articulators removed. Because of the removal of parts of the articulator, a patient’s speech may be distorted and difficult to understand. To overcome this problem, we proposes a joint dictionary training non-negative matrix factorization (JD-NMF) based voice conversion (VC) method. The proposed method can be applied to convert the distorted speech such that it is clear and more intelligible. Experiments results showed that the JD-NMF not only achieves notably higher short-time objective intelligibility (STOI) scores (a standardized objective intelligibility evaluation metric) than those obtained using the original unconverted speech but is also significantly more efficient and effective than a conventional exemplar-based NMF VC method.

 

國立中央大學電機工程學系  (32001) 桃園市中壢區五權里2鄰中大路300號
TEL:(03) 422-7151 轉 34567 , 34568 | FAX:(03) 425-5830 | E-mail:eeoffice@ee.ncu.edu.tw
Copyright © Department of Electrical Engineering, NCU. All Rights Reserved.
隱私權政策聲明