[徵才] 中研院資創中心 徵NLP/ML/DSP專長 博士後
【徵才單位】中研院資創中心 音樂與音訊運算實驗室
Music & Audio Computing Lab,
Research Center for IT Innovation, Academia Sinica
http://mac.citi.sinica.edu.tw/
【職務名稱】博士後 1名
【研究內容】數位信號處理、機器學習、自然語言處理、社群多媒體相關研究
【工作待遇】依中研院/科技部規定 NTD 56,650 起 可議
享勞健保與年終獎金、年終1.5個月
【聘 期】1. 隨到隨審，可隨時起聘
2. 一年一聘
3. 亦接受研發替代役申請
【工作地點】台北市南港區 中研院資創中心
http://www.citi.sinica.edu.tw/
【應徵條件】國內外 電機/資訊 博士學歷
【需求研究專長】
1. natural language processing
2. social multimedia
3. signal processing
4. machine learning
5. information retrieval
【具體研究內容】
參與以下兩研究計畫其中之一
1. Cross-cultural Analysis of Music Perception for Culture-aware Recommendation
The global and extensive use of social media bears an unprecedented
amount of personal and cultural information, which can, to some extent, be
uncovered by state-of-the-art methods from machine learning and social data
science. In combination with the likewise omnipresent consumption and
enjoyment of music around the world, it has become possible to research in a
multifaceted and large scale manner cultural similarities and differences of
music listening behavior. In this project, we set forth to analyze
millions of music-related microblogs collected from Twitter, to investigate
how listening habits, music preferences, and music perception differ
across cultures, and how to model such cultural differences over time, and how
to exploit these differences to improve the state-of-the-art in music
recommendation. This is a joint project with universities in Taiwan, Hong Kong,
and Austria.
2. Complex-Valued Signal Processing and Feature Learning For Music
Information Retrieval
Content analysis of polyphonic music is arguably one of the most challenging
tasks in computer audition, as it tackles the complexity of sound mixtures
with overlapping harmonics components spreading over a wide frequency range.
This project focuses on two research directions to overcome these challenges.
The first is to find novel signal representations for music by using advanced
time-frequency analysis and complex-valued signal processing techniques. The
second is to design robust feature learning methods based on deep learning
and sparse coding techniques. The applications we are interested in including
automatic music transcription, source separation, performance analysis, score
following, and music education.
【聯絡方式】楊奕軒副研究員
http://www.citi.sinica.edu.tw/pages/yang/
yang@citi.sinica.edu.tw
來信請請附履歷、動機、代表著作
【相關連結】
https://tmacw16.wordpress.com/
http://dbis-nowplaying.uibk.ac.at/
http://c4dm.eecs.qmul.ac.uk/ismir15-amt-tutorial/
https://ccrma.stanford.edu/workshops/music-information-retrieval-mir-2015
--
※ 發信站: 批踢踢實業坊(ptt.cc), 來自: 60.199.29.165
※ 文章網址: https://www.ptt.cc/bbs/AfterPhD/M.1455330335.A.EB6.html