Publications

Journal Papers

1. Ming-Han Yang, Yao-Chi Hsu, Hsiao-Tsung Hung, Ying-Wen Chen, Kuan-Yu Chen and Berlin Chen, “Leveraging multi-task learning with neural network based acoustic modeling for improved meeting speech recognition,” International Journal of Computational Linguistics and Chinese Language Processing (IJCLCLP), Vol. 21, No. 2, pp. 85-104, 2016. (in Chinese) [Best Paper Award]

2. Yao-Chi Hsu, Ming-Han Yang, Hsiao-Tsung Hung, Yi-Ju Lin, Kuan-Yu Chen and Berlin Chen, “Evaluation metric-related optimization methods for Mandarin mispronunciation detection,” International Journal of Computational Linguistics and Chinese Language Processing (IJCLCLP), Vol. 21, No. 2, pp. 55- 70, 2016. (in Chinese)

Refereed International Conference Papers

1. Ming-Han Yang, Hung-Shin Lee, Yu-Ding Lu, Kuan-Yu Chen,Yu Tsao, Berlin Chen and Hsin-Min Wang, “Discriminative autoencoders for acoustic modeling,” the 18th Annual Conference of the International Speech Communication Association (Interspeech 2017), Stockholm, Sweden, 2017.

2. Yao-Chi Hsu, Ming-Han Yang, Hsiao-Tsung Hung and Berlin Chen, “Mispronunciation detection leveraging maximum performance criterion training of acoustic models and decision functions,” the 17th Annual Conference of the International Speech Communication Association (Interspeech 2016), San Francisco, USA, 2016.

Refereed Local Conference Papers

1. 林奕儒, 許曜麒, 楊明翰, 陳柏琳, “韻律特徵與聲學特徵於錯誤發音檢測與診斷之研究,” the 2018 Conference on Technologies and Applications of Artificial Intelligence (TAAI 2018), Taichung, Taiwan, 2018. (in Chinese)

2. 許曜麒, 楊明翰, 洪孝宗, 陳冠宇, 陳柏琳, “最佳化錯誤發音檢測效能與監督式錯誤發音診斷之研究,” the 2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI 2016), Hsinchu, Taiwan, 2016. (in Chinese)

3. 楊明翰, 許曜麒, 洪孝宗, 陳柏琳, “華語錯誤發音檢測基於鑑別式訓練之多種深層類神經網路聲學模型與邏輯回歸分析,” the 2015 Conference on Technologies and Applications of Artificial Intelligence (TAAI 2015), Tainan, Taiwan, 2015. (in Chinese)

4. Yao-Chi Hsu, Ming-Han Yang, Hsiao-Tsung Hung, Yuwen Hsiung, Yao-Ting Sung, Berlin Chen, “Exploring combinations of various deep neural network based acoustic models and classification techniques for Mandarin mispronunciation detection,” the 27th International Conference on Computational Linguistics and Speech Processing (ROCLING 2015), Hsinchu, Taiwan, 2015. (in Chinese)

Thesis

• Ming-Han Yang, “Improved neural network based acoustic modeling leveraging multi-task learning and ensemble Learning for meeting speech recognition.” Master Thesis, National Taiwan Normal University, July 2016. (Advisor: Prof. Berlin Chen)