The following publications are possibly variants of this publication:
- Tone nucleus-based multi-level robust acoustic tonal modeling of sentential F0 variations for Chinese continuous speech tone recognitionJin-Song Zhang, Satoshi Nakamura, Keikichi Hirose. speech, 46(3-4):440-454, 2005. [doi]
- Tone nucleus modeling for Chinese lexical tone recognitionJin-Song Zhang, Keikichi Hirose. speech, 42(3-4):447-466, 2004. [doi]
- Tone recognition of continuous Mandarin speech based on neural networksSin-Horng Chen, Yih-Ru Wang. taslp, 3(2):146-150, 1995. [doi]
- Tone recognition of continuous speech of standard Chinese using neural network and tone nucleus modelKeikichi Hirose, Hui Hu, Xiaodong Wang, Nobuaki Minematsu. interspeech 2006: [doi]
- Tone recognition of continuous Cantonese speech based on support vector machinesGang Peng, William S.-Y. Wang. speech, 45(1):49-62, 2005. [doi]
- 0 contours based on tone nucleus model and superpositional modelQinghua Sun, Keikichi Hirose, Nobuaki Minematsu. speech, 54(8):932-945, 2012. [doi]
- Tone Recognition of Continuous Mandarin Speech Based on Hidden Markov ModelYih-Ru Wang, Jyh-Ming Shieh, Sin-Horng Chen. ijprai, 8(1):233-246, 1994.
- Tone Modeling for Continuous Mandarin Speech RecognitionYang Cao, Shuwu Zhang, Taiyi Huang, Bo Xu. ijst, 7(2-3):115-128, 2004. [doi]
- Frameworks for recognition of Mandarin syllables with tones using sub-syllabic unitsChih-Heng Lin, Chien-Hsing Wu, Pei-Yih Ting, Hsin-Min Wang. speech, 18(2):175-190, 1996. [doi]
- Generation of fundamental frequency contours for Mandarin speech synthesis based on tone nucleus modelQinghua Sun, Keikichi Hirose, Wentao Gu, Nobuaki Minematsu. interspeech 2005: 3265-3268 [doi]
- An Investigation of the Target Approximation Model for Tone Modeling and Recognition in Continuous Mandarin SpeechYingming Gao, Xinyu Zhang, Yi Xu, Jinsong Zhang, Peter Birkholz. interspeech 2020: 1913-1917 [doi]
- Maximum entropy based tone modeling for mandarin speech recognitionXinhao Wang, Yansuo Yu, Xihong Wu, Huisheng Chi. icassp 2010: 4850-4853 [doi]