- The tutorial entitled Generative Adversarial Network and its Applications to Signal Processing and Natural Language Processing (slides)
- There are three parts in this tutorial.
- First part (length: 1.5 hours): Giving an introduction of generative adversarial network (GAN) and providing a thorough review about this technology.
- Second part (length: 0.75 hours): Focusing on the applications of GAN to speech signal processing, including speech enhancement, voice conversion, speech synthesis, and the applications of domain adversarial training to speaker recognition and lip reading.
- Third part (length: 0.75 hours): Describing the major challenge of text sentence generation by GAN and reviewing a series of approaches dealing with the challenge. Meanwhile, I will present algorithms that use GAN to achieve text style transformation, unsupervised machine translation, unsupervised abstractive summarization and unsupervised speech recognition.
- The second part of this tutorial is given by Dr. Yu Tsao, and I gave the first and the third parts.
- The tutorial has been given at ICASSP 2018, APSIPA 2018, ISCSLP 2018, and INTERSPEECH 2019.
- This tutorial has the most participants among the 14 tutorials in ICASSP 2018.
- This tutorial has the most participants among the 8 tutorials in INTERSPEECH 2019.
- The talks summarize my recent research (entitled
Towards Machine Comprehension of Spoken Content).
(slides)
- International Invitation
- Microsoft Research Asia (Beijing, July 2017)
- Jinri Toutiao (Beijing, July 2017)
- GPU Technology Conference (San Jose, May 2017)
- Speaker Rating: 4.5/5, Content Rating: 4.36/5
- The talk was given with Prof. Winston Hsu.
- Apple Inc. (San Jose, May 2017)
- Cognitive System Lab, Universität Bremen (Bremen, Germany, January 2017)
- Institute for Natural Language Processing, University of Stuttgart (Stuttgart, Germany, January 2017)
- Mobvoi (Beijing, July 2016)
- Invited Talk at Workshop/Conference
- Intel AI Day in Taiwan with 800 audience (October 2017)
- The South Taiwan Statistics Conference, STSC (June 2017)
- IR workshop, Academia Sinica (November 2016)
- GPU Technology Conference Taiwan (September 2016)
- Invitation Talk for Industry
- CyberLink (August 2017)
- Taipei Fubon Commercial Bank (May 2017)
- Viscovery (January 2017)
- Taishin International Bank (December 2016)
- Appier (July 2016)
- Open Course
- Dosudo deep learning study group (link)
- Course for Technology and Applications of AI and Deep Learning, Industrial Development Bureau (July 2017)
- Annual Meeting of Data Science Lovers with 350 audience (September 2016)
- The talks entitled Spoken Content Retrieval — Beyond Cascading Speech Recognition with Text Retrieval (slides)
- 3-hour Tutorial at Interspeech (San Francisco, September 2016)
- The tutorial was given with Prof. Lin-shan Lee.
- Microsoft Research (Redmond, July 2014)
- Google Headquarter (Mountain View, June 2014)
- Department of Computer Science & Information Engineering of National Taiwan University (March 2014)
- Department of Electrical Engineering of National Taiwan University (March 2014)
- MIT CSAIL (Boston, September 2013)