SPE-28.1
A UNIVERSAL ORDINAL REGRESSION FOR ASSESSING PHONEME-LEVEL PRONUNCIATION
Shaoguang Mao, Frank Soong, Yan Xia, Jonathan Tien, Microsoft Research Asia, China
Session:
Pronunciation Assessment
Track:
Speech and Language Processing
Location:
Gather Area E
Presentation Time:
Mon, 9 May, 22:00 - 22:45 China Time (UTC +8)
Mon, 9 May, 14:00 - 14:45 UTC
Mon, 9 May, 14:00 - 14:45 UTC
Session Chair:
William Hartmann, Raytheon BBN
Session SPE-28
SPE-28.1: A UNIVERSAL ORDINAL REGRESSION FOR ASSESSING PHONEME-LEVEL PRONUNCIATION
Shaoguang Mao, Frank Soong, Yan Xia, Jonathan Tien, Microsoft Research Asia, China
SPE-28.2: A TRANSFER LEARNING APPROACH FOR PRONUNCIATION SCORING
Marcelo Sancinetti, Jazmín Vidal, Cyntia Bonomi, Universidad de Buenos Aires, Argentina; Luciana Ferrer, Consejo Nacional de Investigaciones y Técnicas, Argentina
SPE-28.3: EXPLORING NON-AUTOREGRESSIVE END-TO-END NEURAL MODELING FOR ENGLISH MISPRONUNCIATION DETECTION AND DIAGNOSIS
Hsin-Wei Wang, Bi-Cheng Yan, Berlin Chen, National Taiwan Normal University, Taiwan; Hsuan-Sheng Chiu, Chunghwa Telecom Laboratories, Taiwan; Yung-Chang Hsu, EZAI, Taiwan
SPE-28.4: PHONEME MISPRONUNCIATION DETECTION BY JOINTLY LEARNING TO ALIGN
Binghuai Lin, Liyuan Wang, Tencent Technology Co., Ltd, China
SPE-28.5: AN APPROACH TO MISPRONUNCIATION DETECTION AND DIAGNOSIS WITH ACOUSTIC, PHONETIC AND LINGUISTIC (APL) EMBEDDINGS
Wenxuan Ye, Zhiyong Wu, Tsinghua University, China; Shaoguang Mao, Frank Soong, Wenshan Wu, Yan Xia, Jonathan Tien, Microsoft Research Asia, China
SPE-28.6: MASKED ACOUSTIC UNIT FOR MISPRONUNCIATION DETECTION AND CORRECTION
Zhan Zhang, Yuehai Wang, Jianyi Yang, Zhejiang University, China