研發人才




蔡偉和

電子工程系

學經歷:
  1.飛利浦研發工程師
2.中研院資訊所博士後研究
3.本校計網中心行政及諮詢組組長

專業技術
  數位信號處理、互動式娛樂服務之音訊處理技術
   
研發介紹
  ◎ 期刊論文
  "Speech Utterance Clustering Based on the Maximization of Within-cluster Homogeneity of Speaker Voice Characteristics",The Journal of the Acoustical Society of America,1631-1645,2006/9/1(SCI)

"A Music Retrieval System Based on Query-by-Singing for Karaoke Jukebox",Lecture Notes in Computer Science,445-459,2006/10/1(SCI)

"Automatic Identification of the Sung Language in Popular Music Recordings",Journal of New Music Research,105-114,2007/9/1(SCI)

"Automatic Speaker Clustering Using A Voice Characteristic Reference Space and Maximum Purity Estimation",IEEE Transactions on Audio, Speech and Language Processing,1461-1474,2007/5/1(SCI)

"Evolutionary Minimization of the Rand Index for Speaker Clustering," Computer Speech and Language",Computer Speech and Language,165-175,2009/1/1(SCI)

"Speaker Clustering Based on Bayesian Information Criterion",Journal of Information Science and Engineering,1873-1886,2008/12/1(SCI)

"Using the Similarity of Main Melodies to Identify Cover Versions of Popular Songs for Music Document Retrieval",Journal of Information Science and Engineering,1669-1687,2008/12/1(SCI)

"基於梅爾頻譜質心倒頻譜係數之音樂聲紋辨識研究",資訊科技國際期刊,18-31,2008/12/1(ELSE1)

"Improving GMM-UBM Speaker Verification Using Discriminative Feedback Adaptation",Computer Speech and Language,376-388,2009/7/1(SCI)

"Improving the Characterization of the Alternative Hypothesis via Minimum Verification Error Training with Applications to Speaker Verification",Pattern Recognition,1351-1360,2009/7/1(SCI)

"Using Kernel Discriminant Analysis to Improve the Characterization of the Alternative Hypothesis for Speaker Verification",IEEE Transactions on Audio, Speech and Language Processing,1675-1684,2008/11/1(SCI)

"A query-by-singing system for retrieving karaoke music",IEEE Transactions on Multimedia,1626-1637,2008/12/1(SCI)

"Speaker Identification in Overlapping Speech",Journal of Information Science and Engineering,1-13,2010/9/1(SCI)

"Clustering Unknown Music Recordings Based on Audio Fingerprinting",International Journal of Computer Science and Software Technology,119-130,2010/7/1(ELSE2)

"Background Music Removal Based on Cepstrum Transformation for Popular Singer Identification",IEEE Transactions on Audio, Speech, and Language Processing,1196-1205,2011/7/1(SCI)
  ◎ 研討會論文
  "On maximizing the within-cluster homogeneity of speaker voice characteristics for speech utterance clustering",IEEE Conference on Acoustics, Speech, and Signal Processing,Toulouse,2006/5/14

"A Kernel-based Discrimination Framework for Solving Hypothesis Testing Problems with Application to Speaker Verification",International Conference on Pattern Recognition,香港,2006/8/20

"Improving the Characterization of the Alternative Hypothesis via Kernel Discriminant Analysis for Likelihood Ratio-based Speaker Verification",Proc. International Conference on Spoken Language Processing,Pittsburgh,2006/9/17

"A Music Retrieval System based on Query-by-singing for Karaoke Jukebox",Asian Information Retrieval Symposium,Singapore,2006/10/16

"Speaker Clustering Based on Minimum Rand Index",IEEE Conference on Acoustics, Speech, and Signal Processing,Hawaii,2007/4/15

"Speaker Clustering Using Direct Maximization of A BIC-based Score",European Conference on Speech Communication and Technology (Interspeech-Eurospeech),Antwerp,2007/8/27

"Automatic Identification of Simultaneous Singers in Duet Recordings",Proc. International Conference on Music Information Retrieval,Philadelphia,2008/9/14

"Evolutionary Minimum Verification Error Learning of the Alternative Hypothesis Model for LLR-based Speaker Verification",Proc. The Tenth European Conference on Speech Communication and Technology,Antwerp,2007/8/27

"結合頻譜質心法與梅爾頻率濾波器之音樂聲紋辨識",2008資訊科技國際研討會,台中,2008/4/25

"重唱曲之歌手識別研究",2008電腦音樂與音訊技術研討會,台北,2008/5/24

"非督導式音樂曲風分類",電子工程技術研討會,高雄,2008/6/19

"Discriminative Feedback Adaptation for GMM-UBM Speaker Verification",International Symposium on Chinese Spoken Language Processing,Kunming,2008/12/16

"Clustering Music Recordings by Their Keys",International Conference on Music Information Retrieval,Philadelphia,2008/9/14

"Blind Clustering of Music Recordings Based on Audio Fingerprinting",International Conference on Intelligent Information Hiding and Multimedia Signal Processing,Kyoto,2009/9/12

"Clustering Music Recordings Based on Genres",International Conference on Information Science and Applications,Seoul,2010/4/21
  ◎ 專書著作
  "數位信號處理平台在嵌入式系統的應用",文魁資訊, 出版日期:2006/12/1, ISBN:978-986-125-887-4

"單晶片於數位信號處理的應用",文魁圖書, 出版日期:2007/10/1, ISBN:ISBN 9789862040676

"單晶片數位訊號處理平台之開發速成寶典",五南圖書出版股份有限公司, 出版日期:2012/8/1, ISBN:978-957-11-6740-4
  ◎ 研究計畫
  "流行音樂之歌唱語言辨識方法研究",國科會專題研究計畫NSC95-2218-E-027-020,2006/8/1~2007/7/31

"音訊內容之語者自動分段標記(I)",國科會專題研究計畫NSC96-2628-E-001-024-MY3,2007/8/1~2008/7/31

"範例式音樂檢索技術研究(I)",國科會專題研究計畫NSC 96-2221-E-027 -097 -MY3,2007/8/1~2008/7/31

"音訊內容之語者自動分段標記(II)",國科會專題研究計畫NSC96-2628-E-001-024-MY3,2008/8/1~2009/7/31

"範例式音樂檢索技術研究(II)",國科會專題研究計畫NSC 96-2221-E-027 -097 -MY3,2008/8/1~2009/7/31

"範例式音樂檢索技術研究(III)",國科會專題研究計畫NSC 96-2221-E-027 -097 -MY3,2009/8/1~2010/7/31

"音訊內容之語者自動分段標記(III)",國科會專題研究計畫NSC96-2628-E-001-024-MY3,2009/8/1~2010/7/31

"以語音辨識為基礎的互動式行動廣告服務",國科會產學計畫案NSC 98-2622-E-027 -035 -CC3,2009/11/1~2010/10/31

"自動歌唱評分方法研究",國科會專題研究計畫99-2628-E-027-005-,2010/8/1~2011/7/31

"自動歌唱評分方法研究(II)",國科會專題研究計畫NSC 100-2628-E-027 -002 -,2011/8/1~2012/7/31

"應用於廣場電子看板之互動式遊戲的語音辨識技術研發",國科會專題研究計畫100-2622-E-027-012-CC3,2011/6/1~2012/5/31

"教育部補助網路資訊人才培育計畫-數位匯流100年度課程發展計畫(設備費)-影音娛樂服務平台整合",教育部委訓計畫7002206,2011/4/1~2012/3/31

"錄音資料之關鍵詞偵測技術研發",企業產學計畫案2012212,2012/6/1~2013/5/30

"利用音樂療法並結合腦波分析及音訊辨識技術進行駕駛疲勞度改善研究",國科會專題研究計畫101-2221-E-027-128-MY2,2012/8/1~2013/7/31

"自動歌唱評分方法研究(3/3)",國科會專題研究計畫101-2628-E-027-001-,2012/8/1~2013/7/31
   
專利介紹
 
  基於語音辨識的互動式廣告系統(一種以語音辨識為基礎的互動式行動廣告服務  
本發明提供一種基於語音辨識的互動式廣告系統,其中包含一接收模組、一確認模組以及一廣告訊息產生模組。該......
 
  一種卡拉OK唱歌評分方法  
一種唱歌評分系統,包括一歌曲存放單元、一基於音高之分析模組、一基於音量之分析模組、一基於節奏之分析模......
 
 
  用於改善輕聲細語下之語者確認的爆音處理系統及其方法  
一種用於改善輕聲細語下之語者確認的爆音處理系統及其方法,係設置於一具有收音模組之電子裝置內,該爆音處......