Download presentation
Presentation is loading. Please wait.
Published byCynthia Wilkinson Modified over 9 years ago
1
Some Research Activities in MIR Lab J.-S. Roger Jang ( 張智星 ) jang@cs.nthu.edu.tw http://www.cs.nthu.edu.tw/~jang Multimedia Information Retrieval Lab CS Dept, Tsing Hua Univ, Taiwan
2
-2- Outline zSpeech Assessment zSinging Voice Separation zAudio Music Annotation
3
-3- Demo: Practice of Mandarin Idioms of Length 4 ( 一語中的 ) yLevel (difficulty) of an idiom is based on it’s freq. via Google search: x 孤掌難鳴 ===> 260,000 x 鶼鰈情深 ===> 43,300 x 亡鈇意鄰 ===> 22,700 x 舉案齊眉 ===> 235,000 yCan be adapted for English learning yNext step: multi- threading, fast decoding via FSM
4
-4- Demo: Recitation Machine (唸唸不 忘) zSupport Mandarin & English zSupport user-defined recitation script zNext step: multithreading for recording & recognition
5
-5- Demo: Dialog Practice via Videos zDialog-based practice and evaluation
6
-6- Demo: Embedded Systems yChicken run ( 落跑雞 )Chicken run ( 落跑雞 yPenguin for Tang Poetry ( 唐詩企鵝 )Penguin for Tang Poetry ( 唐詩企鵝 ) yRobot Fighter ( 蘿蔔戰士 )Robot Fighter ( 蘿蔔戰士 ) ySinging Bass & Dog ( 大 嘴鱸魚和唱歌狗 )Singing Bass & Dog ( 大 嘴鱸魚和唱歌狗 )
7
-7- Speech Assessment: Current/Future Directions zOn-going work: yTone recognition and assessment yRetroflex & nonretroflex recognition yDetection of “ 兒化音 ” zResearch directions yIdentification of confusing phone/syllables yScore optimization schemeScore optimization scheme zDemo page: yhttp://mirlab.org/mir_main/demo.htmhttp://mirlab.org/mir_main/demo.htm
8
-8- Singing Voice Separation zChao-Ling Hsu, Jyh-Shing Roger Jang, and Te-Lu Tsai, "Separation of Singing Voice from Music Accompaniment with Unvoiced Sounds Reconstruction for Monaural Recordings", Proceedings of 125th AES Convention, San Francisco, USA, Oct. 2008.Chao-Ling Hsu, Jyh-Shing Roger Jang, and Te-Lu Tsai, "Separation of Singing Voice from Music Accompaniment with Unvoiced Sounds Reconstruction for Monaural Recordings", Proceedings of 125th AES Convention, San Francisco, USA, Oct. 2008.
9
-9- SVS: Current/Future Directions zAudio Melody Extraction yClose the loop: pitch vocal better pitch better vocal … zLack of a public-domain dataset yWe are preparing one… zMore error analysis is under way.
10
-10- Audio Music Annotation & Retrieval zZhi-Sheng Chen, Jia-Min Zen, Jyh-Shing Roger Jang, "Music Annotation and Retrieval System Using Anti-Models", Proceedings of 125th AES Convention, San Francisco, USA, Oct. 2008.Zhi-Sheng Chen, Jia-Min Zen, Jyh-Shing Roger Jang, "Music Annotation and Retrieval System Using Anti-Models", Proceedings of 125th AES Convention, San Francisco, USA, Oct. 2008
11
-11- Research Directions z“Glass ceiling” problem yPointed by Stephen Downie, “The music information retrieval evaluation exchange (2005– 2007):A window into music information retrieval research” yWe should go beyond spectral-based approaches to have more semantic models/representations zInterpretation of “Sad” and “Stong”: Probability of fuzziness?
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.