Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2013, Vol. 14 Issue (11): 835-844    DOI: 10.1631/jzus.C1300104
    
Exploiting articulatory features for pitch accent detection
Junhong Zhao, Ji Xu, Wei-qiang Zhang, Hua Yuan, Jia Liu, Shanhong Xia
State Key Laboratory of Transducer Technology, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100190, China; National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
Download:   PDF(0KB)
Export: BibTeX | EndNote (RIS)      

Abstract  Articulatory features describe how articulators are involved in making sounds. Speakers often use a more exaggerated way to pronounce accented phonemes, so articulatory features can be helpful in pitch accent detection. Instead of using the actual articulatory features obtained by direct measurement of articulators, we use the posterior probabilities produced by multi-layer perceptrons (MLPs) as articulatory features. The inputs of MLPs are frame-level acoustic features pre-processed using the split temporal context-2 (STC-2) approach. The outputs are the posterior probabilities of a set of articulatory attributes. These posterior probabilities are averaged piecewise within the range of syllables and eventually act as syllable-level articulatory features. This work is the first to introduce articulatory features into pitch accent detection. Using the articulatory features extracted in this way, together with other traditional acoustic features, can improve the accuracy of pitch accent detection by about 2%.

Key wordsArticulatory features      Pitch accent detection      Prosody      Computer-aided language learning (CALL)      Multi-layer perceptron (MLP)     
Received: 22 April 2013      Published: 06 November 2013
CLC:  TP391  
  TN912.34  
Cite this article:

Junhong Zhao, Ji Xu, Wei-qiang Zhang, Hua Yuan, Jia Liu, Shanhong Xia. Exploiting articulatory features for pitch accent detection. Front. Inform. Technol. Electron. Eng., 2013, 14(11): 835-844.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.C1300104     OR     http://www.zjujournals.com/xueshu/fitee/Y2013/V14/I11/835


Exploiting articulatory features for pitch accent detection

Articulatory features describe how articulators are involved in making sounds. Speakers often use a more exaggerated way to pronounce accented phonemes, so articulatory features can be helpful in pitch accent detection. Instead of using the actual articulatory features obtained by direct measurement of articulators, we use the posterior probabilities produced by multi-layer perceptrons (MLPs) as articulatory features. The inputs of MLPs are frame-level acoustic features pre-processed using the split temporal context-2 (STC-2) approach. The outputs are the posterior probabilities of a set of articulatory attributes. These posterior probabilities are averaged piecewise within the range of syllables and eventually act as syllable-level articulatory features. This work is the first to introduce articulatory features into pitch accent detection. Using the articulatory features extracted in this way, together with other traditional acoustic features, can improve the accuracy of pitch accent detection by about 2%.

关键词: Articulatory features,  Pitch accent detection,  Prosody,  Computer-aided language learning (CALL),  Multi-layer perceptron (MLP) 
[1] Gopi Ram , Durbadal Mandal , Sakti Prasad Ghoshal , Rajib Kar . Optimal array factor radiation pattern synthesis for linear antenna array using cat swarm optimization: validation by an electromagnetic simulator[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(4): 570-577.
[2] Yuan-ping Nie, Yi Han, Jiu-ming Huang, Bo Jiao, Ai-ping Li. Attention-based encoder-decoder model for answer selection in question answering[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(4): 535-544.
[3] Lin-bo Qiao, Bo-feng Zhang, Jin-shu Su, Xi-cheng Lu. A systematic review of structured sparse learning[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(4): 445-463.
[4] Rong-Feng Zhang , Ting Deng , Gui-Hong Wang , Jing-Lun Shi , Quan-Sheng Guan . A robust object tracking framework based on a reliable point assignment algorithm[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(4): 545-558.
[5] . A quality requirements model and verification approach for system of systems based on description logic[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(3): 346-361.
[6] Ali Darvish Falehi, Ali Mosallanejad. Dynamic stability enhancement of interconnected multi-source power systems using hierarchical ANFIS controller-TCSC based on multi-objective PSO[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(3): 394-409.
[7] Wen-yan Xiao, Ming-wen Wang, Zhen Weng, Li-lin Zhang, Jia-li Zuo. Corpus-based research on English word recognition rates in primary school and word selection strategy[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(3): 362-372.
[8] Li Weigang. First and Others credit-assignment schema for evaluating the academic contribution of coauthors[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(2): 180-194.
[9] Hui Chen, Bao-gang Wei, Yi-ming Li, Yong-huai Liu, Wen-hao Zhu. An easy-to-use evaluation framework for benchmarking entity recognition and disambiguation systems[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(2): 195-205.
[10] Jun-hong Zhang, Yu Liu. Application of complete ensemble intrinsic time-scale decomposition and least-square SVM optimized using hybrid DE and PSO to fault diagnosis of diesel engines[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(2): 272-286.
[11] Yue-ting Zhuang, Fei Wu, Chun Chen, Yun-he Pan. Challenges and opportunities: from big data to knowledge in AI 2.0[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(1): 3-14.
[12] Bo-hu Li, Hui-yang Qu, Ting-yu Lin, Bao-cun Hou, Xiang Zhai, Guo-qiang Shi, Jun-hua Zhou, Chao Ruan. A swarm intelligence design based on a workshop of meta-synthetic engineering[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(1): 149-152.
[13] Yong-hong Tian, Xi-lin Chen, Hong-kai Xiong, Hong-liang Li, Li-rong Dai, Jing Chen, Jun-liang Xing, Jing Chen, Xi-hong Wu, Wei-min Hu, Yu Hu, Tie-jun Huang, Wen Gao. Towards human-like and transhuman perception in AI 2.0: a review[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(1): 58-67.
[14] Yu-xin Peng, Wen-wu Zhu, Yao Zhao, Chang-sheng Xu, Qing-ming Huang, Han-qing Lu, Qing-hua Zheng, Tie-jun Huang, Wen Gao. Cross-media analysis and reasoning: advances and directions[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(1): 44-57.
[15] Le-kui Zhou, Si-liang Tang, Jun Xiao, Fei Wu, Yue-ting Zhuang. Disambiguating named entities with deep supervised learning via crowd labels[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(1): 97-106.