张劲松　


一.教育经历
张劲松，男，工学博士。1989年合肥工业大学计算机信息系学士，1992年中国科技大学电子技术专业硕士，2000年日本东京大学电子情报专业语音专攻博士。2000年-2007年在国际通信基础技术研究所ATR（日本）从事研究工作，历经博士后研究员、研究员和主任研究员。2006年受聘北京语言大学对外汉语研究中心客座教授。2007年底入职北京语言大学信息科学学院，2008年北京语言大学汉语研究中心研究员。主要研究领域和方向: 语音识别、合成技术、韵律建模、实验语音学、语音习得、基于语音识别、合成技术的计算机辅助语音教学技术。1990年以来主要从事语音识别系统和中文韵律信息处理的研究，参与了中国国家自然科学基金资助项目（“汉语连续语音识别和理解系统的研究”、“基于话者聚类的话者自适应语音识别技术的研究”、“基于韵律信息的汉语语音识别技术”）、日本总务省（“日中, 日英语音翻译系统的研究和开发”）、日本文部省（“中文韵律及声调处理技术”）、日本情报通信研究机构（“日英、日中旅行会话翻译系统”）、教育部人文科学基地重大项目（“面向外国学生的计算机辅助汉语语音正音系统的研究”）等科研项目。目前的研究兴趣主要在基于计算机语音技术的高效二语语音习得技术。现为全国人机语音通信学术会议NCMMSC常设机构委员，NCMMSC学术交流工作组长，ISCA（国际语言交流协会）、IPA（国际语音协会）、ASJ（日本声学协会），中国语音、中文信息处理、中国声学等学会委员。担任了国内外多家学术杂志审稿人工作，包括IEEE Trans. On Speech and Audio Processing, Speech Communication, Computer Speech and Language, Journal of Phonetics, IEICE Trans. On Information and Systems, 自动化学报, 世界汉语教学，计算机工程应用等。 曾获ATR 2004 显著功绩表彰，2007IEICE优秀论文奖。在国际学术会议及国内外期刊上已发表七十余篇研究论文，其中被SCI、EI、ISTP检索论文二十余篇。
二.基本资料
职务职称：教授，博士生导师，博士后合作导师
研究方向：语音识别、合成技术、韵律建模、实验语音学、语音习得、基于语音识别、合成技术的计算机辅助语音教学技术
开设课程：1.电路分析基础 2.语音信息处理 3.韵律信息处理 4.语言学学术前沿与创新
办公电话：**
电子邮箱：jinsong.Zhang@blcu.edu.cn


三.研究成果:
l Journals
1. 曹文，张劲松，“面向计算机辅助正音的汉语中介语语音语料库的创制与标注”，《语言文字应用》，2009，4. pp.122-131.
2. Xiao-Dong Wang, Keikichi Hirose, Jin-Song Zhang, Nobuaki Minematsu, Tone Recognition of Continuous Mandarin Speech Based on Tone Nucleus Model and Neural Network, IEICE TRANSACTIONS on Information and Systems，2008, Vol.E91-D No.6 pp.1748-1755， (SCI: 315EP, EI: 762)
3. Zhang Jinsong，Takatoshi Jitsuhiro，Hirofumi Yamamoto，HU Xinhui，Satoshi Nakamura， An Introduction to Chinese Speech Recognition Frontend of NiCT/ATR Multi-Lingual Speech Translation System，Tsinghua Science and Technology, 2008 13(4), pp.545-552. (EI: 615)
4. Tohru Shimizu, Yutaka Ashikari, Eiichiro Sumita , Jinsong Zhang, Satoshi Nakamura, NICT-ATR Chinese-Japanese-English Speech-to-Speech Translation System, Tsinghua Science and Technology, 2008 13(4), pp.540-544. (EI: 629)
5. CAO Wen, ZHANG Jinsong， “A Perspective Study on the Tone-3 Accent in Chinese Intonation”，Tsinghua Science and Technology, 2008 13(4), pp.533-539 (EI: 613).
6. Jin-Song Zhang, Xin-hui Hu, Satoshi Nakamura, Using Mutual Information Criterion to Design An Efficient Phoneme Set For Chinese Speech Recognition, IEICE Transaction on INFO. & SYST., Vol.91-D, No. 3, pp.508-513，March 2008. (SCI: 282ZL, EI: 617)
7. Jin-Song Zhang, Satoshi Nakamura, An Improved Greedy Search Algorithm For The Development of A Phonetically Rich Speech Corpus, IEICE Transaction on INFO. & SYST., Vol.91-D, No. 3, pp.615-630, March 2008. (SCI:282ZL, EI: 629)
8. Satoshi Nakamura, Konstantin Markov, Hiromi Nakaiwa, Genichi Kikui, Hisashi Kawai, Takatoshi Jitsuhiro, Jin-Song Zhang, Hirofumi Yamamoto, Eiichiro Sumita and Seiichi Yamamoto, "The ATR multi-lingual speech-to-speech translation system", IEEE Trans. on Speech and Audio Processing, Vol.14(2), pp.365-376, March, 2006. (SCI:016IX, EI: 835)
9. Jin-Song Zhang, Satoshi Nakamura, Keikichi Hirose, "Tone Nucleus Based Multi-level Robust Acoustic Tonal Modeling of Sentential F0 Variations for Chinese Continuous Speech Tone Recognition", Elsevier Science, Speech Communication, Vol. 46(3-4), (2005) 440-454, (SCI:949QW, EI: 78)
10. Jin-Song Zhang, Keikichi Hirose, "Tone nucleus modeling for Chinese lexical tone recognition", Elsevier Science, Speech Communication, 42, pp.447-466, 2004. (SCI:814YB, EI: 28)
11. Jin-Song Zhang, Konstantin Markov, Tomoko Matsui and Satoshi Nakamura, "A study on acoustic modeling of pauses for recognizing noisy conversational speech", IEICE Transaction on INFO. & SYST., Vol.86-D, No. 3, March 2003. (SCI & SSCI:653EG, EI: 11)
12. Konstantin Markov, Tomoko Matsui, Rainer Gruhn, Jin-Song Zhang, and Satoshi Nakamura, "Noise and channel distortion robust ASR system for DARPA SPINE2 task", IEICE Transaction on INFO. & SYST., Vol.86-D, No. 3, March 2003. (SCI:653EG, EI: 12)
13. Shu-Wu Zhang, Jin-Song Zhang, "Towards Chinese-Japanese speech communication—ATR approach to recognizing Chinese Mandarin Speech", ATR Journal, No. 44, Summer, 2001.
14. 戴蓓倩，郁正庆，戴任飞，张劲松，王长富，司虎，“基于话者分类的HMM的话者自适应语音识别”，中国科学技术大学学报 ISSN:0253-2778, 1996, 26(2):147-153。
15. 王长富，林志钢，戴蓓倩，张劲松，“基于小波变换的语音基音周期检测”，中国科学技术大学学报 ISSN:0253-2778, 1995, 25(1): 47-52。
16. 戴蓓倩，朱斌，张劲松，王长富，李辉，“基于组合神经网络和模糊聚类的话者分类”，中国科学技术大学学报 ISSN:0253-2778, 1997, 27(1):25-
17. 戴蓓倩，郁正庆，张劲松，王长富，“基于FVQ和HMM模糊训练的语音识别方法”，中国科学技术大学学报 ISSN:0253-2778, 1994, 24(2):161-167。
18. 张劲松，戴蓓倩，“基于知识和模糊决策的连续语音的约束匹配”，中国科学技术大学学报 ISSN:0253-2778, 1993, 23(2):145-150。
l Book chapters
19. 王东宁, 曹文, 张劲松,"对外汉语语音语料库的标注质量评价",《汉语国际教育“三教”问题探索》，外语教学与研究出版社，pp.332-343, 2010, 10
20. 张劲松, 侯玉霞, 曹文, “连续语流中声学基元信息冗余度初考”, 《汉语国际教育“三教”问题探索》，外语教学与研究出版社，pp.372-385, 2010, 10
21. ZHANG Jinsong, CAO Wen, "Studies on Chinese Tone Information Processing and Their Possible Implication for Automatic Pronunciation Training", 《现代语音学前沿文集》, 2009, 商务印书馆，pp.391-402.
22. Jin-Song Zhang, Satoshi Nakamura and Keikichi Hirose, "Tonal contextual F0 variations and anchoring based discrimination", 《汉语言文字学论丛》，北京语言大学出版社，pp.17-30, 2008.
l International conferences
23. Wei Li, Jinsong Zhang, Wen Cao, A Study On Functional Loads of Word Boundaries Based On Mutual Information of Chinese Text And Phonemes, 2011 RISP International Workshop on Nonlinear Circuits and Signal Processing, (NCSP11), Tianjin, China, March, 2011.
24. Jinsong Zhang, Wei Li, Yuxia Hou, Wen Cao, Ziyu Xiong, A Study On Functional Loads of Phonetic Contrasts Under Context Based On Mutual Information of Chinese Text And Phonemes, The 7^th International Symposium on Chinese Spoken Language Processing (ISCSLP), Tainan, Nov. 2010，pp.194-198 ( EI: 284).
25. Jinsong Zhang, Dongning Wang, Wen Cao, Ziyu Xiong, A Distinctive Feature Based Method For Evaluating The Phonetic Transcription Of A Non-Native Speech Database, The 7^th International Symposium on Chinese Spoken Language Processing (ISCSLP), Tainan, Nov. 2010, pp.416-419 (EI: 230).
26. Wen Cao, Dongning Wang, Jinsong Zhang(Corresponding Author), Ziyu Xiong，Developing A Chinese L2 Speech Database of Japanese Learners With Narrow-Phonetic Labels For Computer Assisted Pronunciation Training，InterSpeech2010, pp.1922-1925, Tokyo, Japan, Sept. 2010, pp.1922-1925 (to be indexed by ISI)
27. Xinhui Hu, Hirofumi Yamamoto, Jinsong Zhang, Keiji Yasuda, Youzheng Wu and Hideki Kashioka, “Utilization of Huge Written Text Corpora for Conversational Speech Recognition”, The 6^th International Symposium on Chinese Spoken Language Processing (ISCSLP), Kunming, ISBN: 978-1-4244-2942-4, pp.97-100, 2008 Dec(EI: 042, ISTP:BJA83).
28. Xiao-Dong Wang, K. Hirose, J.-S. Zhang, N. Minematsu, Tone recognition of continuous speech of statndard Chinese Assisted by MLP and Tone Nucleus Model, 2007 RISP International Workshop on Nonlinear Circuits and Signal Processing, (NCSP07), pp.571-574
29. Jin-Song Zhang, Xinhui-hu and Satoshi Nakamura, "Automatic Derivation of A Phoneme Set With Tone Information for Chinese Speech Recognition Based on Mutual Information Criterion", ICASSP 2006,, May, 2006 (EI: 370, ISTP:BFZ22).
30. Jin-Song Zhang, Satoshi Nakamura and Keikichi Hirose, "Efficient tone classification of speaker independent continuous Chinese speech using anchoring based discriminating features", Proc. of International conference on spoken language processing (ICSLP) 2004, pp. 809-812.
31. Satoshi Nakamura, Konstantin Markov, Takatoshi Jitsuhiro, Jin-song Zhang, Hirofumi Yamamoto and Genichiro Kikui, "Multi-lingual speech recognition system for Speech-To-Speech Translation", Proceedings from International Workshop on Spoken Language Translation (IWSLT), Kyoto, Japan, Oct. 2004, pp.147-154.
32. Jin-Song Zhang, Keikichi Hirose, "A Study on robust segmentation and location of tone nuclei in Chinese continuous speech", Proc. of ICASSP, Vol. I, pp. 913-916,, May 2004.(EI: 62, ISTP:BAG99).
33. Jin-Song Zhang, Satoshi Nakamura and Keikichi Hirose, "Robust acoustic modeling of contextual tonal F0 variations on the basis of tone nucleus framework", International symposium on Tonal Aspects of Languages (TAL2004), Beijing, March, 2004, pp.239-242.
34. Jin-Song Zhang, Satoshi Nakamura and Keikichi Hirose, "Tonal contextual F0 variations and anchoring based discrimination", International congress on Speech Prosody (SP2004), Nara, Japan, March, 2004, pp.525-528.
35. Jin-Song Zhang, Keikichi Hirose and Satoshi Nakamura, "A multilevel framework to model the inherently confounding nature of sentential F0 contours for recognizing Chinese lexical tones", IEEE international conference on Acoustics, Speech and Signal Processing (ICASSP), Vol. I, pp.776-780, Hong Kong, 2003. (EI: 54, ISTP:BX44W).
36. Jin-Song Zhang and Satoshi Nakamura, "An efficient algorithm to search for a minimum sentence set for collecting speech database", International Congress on Phonetic Science (ICPhS), pp.3145-3148, Barcelona, Spain, August, 2003.
37. Jin-Song Zhang and Satoshi Nakamura, "Modeling varying pauses to develop robust acoustic models for recognizing noisy conversational speech", Proc. of International conference on Spoken Language Processing (ICSLP) 2002, pp.2601-2604, Denver, U.S., September, 2002.
38. Sheng Gao, Jin-Song Zhang, Satoshi Nakamura, Chin-hui Lee and Tat-seng Chua, "Weighted graph based decision tree optimization for high accuracy acoustic modeling", Proc. of ICSLP 2002, pp.1233-1236.
39. J.-S. Zhang, Sh.-W. Zhang, Y. Sagisaka, and S. Nakamura, “A hybrid approach to enhance task portability of acoustic models in Chinese speech recognition”, Proc. of Eurospeech2001, Denmark, Sept. 2001. Vol.3, pp.1661-1663.
40. J.-S. Zhang, S. Nakamura and K. Hirose, “Discriminating Chinese lexical tones by anchoring F0 features”, Proc. of ICSLP2000, Beijing, China, Oct. 2000. Vol. II, pp.87-90.
41. J.-S. Zhang, K. Hirose, “Anchoring hypothesis and its application to tone recognition of Chinese continuous speech”, Proc. of ICASSP2000, Istanbul, Turkey, June, 2000, Vol. III, pp1419-1422. (EI: 26, ISTP:BQ62X).
42. J.-S. Zhang, H. Kawanami, “Modeling Carryover and Anticipation effects for Chinese tone recognition”, Proc. of Eurospeech’99, Budapest, Hungary, Sep. 1999. pp.747-750.
43. K. Hirose, J.-S. Zhang, “Tone recognition of Chinese continuous speech using Tone Critical segments”, Proc. of Eurospeech’99, Budapest, Hungary, Sep. 1999. pp.879-882.
44. J.-S. Zhang, G. Kawai, K. Hirose, “Subsyllabic tone units for reducing physiological effects in automatic tone recognition for connected Mandarin Chinese”, Proc. from International Congress on Phonetic Science (ICPhS) XIV, San Francisco, USA, Aug. 1999, pp.2367-2370.
45. J.-S. Zhang, K. Hirose, “A robust tone recognition method of Chinese based on sub-syllabic F0 contours”, ICSLP98, Sydney, Australia, Dec. 1998, pp. 703-706.
46. C.-F. Wang, B-q Dai, J.-S. Zhang, H. Li, Y. Liu, "Scheme for high quality linear prediction analysis of speech", Proceedings from International Conference on Signal Processing, ICSP, Vol. 1, 1996, pp.694-697. (EI: **05).
47. J.-S. Zhang, B-q Dai, C-f Wang, H-k Kwan, K. Hirose, “Adaptive Recognition Method Based on Posterior Use of Distribution Pattern Of Output Probabilities”. ICSLP96, Oct. 1996, pp.1129-1132. (EI: **89).
48. J.-S. Zhang, B-q Dai, S. Xu, “Introduction of Consonant Duration Rules to Chinese Syllable Recognition”, Japan-China Symposium on Advanced Information Technology, Univ. of Tokyo, Tokyo, Sep., 1994, pp.49-54.
49. J.-S. Zhang, B-q Dai, “Study on Improvement of Robustness of A Chinese Isolated Word Recognition System Based on SCHMM”, Proceedings of International Conference on Signal Processing,. Oct. 1993, pp. 658-661.
l National conferences(中国/日本)
49. 侯玉霞, 曹文, 张劲松, 基于大规模语料库的汉语声学区别特征信息量调查, 第九届中国语音学学术会议论文集, 天津南开大学，2010，5
50. Wang Dongning, Cao Wen, Zhang Jinsong, Consistency of manual annotation and segmentation of Mandarin Chinese spoken by Japanese learners, 第九届中国语音学学术会议论文集，天津南开大学，2010，5
51. 曹文，张劲松, 面向计算机辅助正音语音语料库的创制与标注, NCMMSC 论文集 2009，8
52. J.-S. Zhang and, A study on Different Unit Based Chinese Langauge Models for Spontaneous Speech Recognition, Proc. of the he Acoustic Society of Japan (ASJ), 2007 Spring, March. pp.173-174
53. X.-D. Wang, K. Hirose, J.-S. Zhang, N. Minematsu, Zh.-Y. Jiang, Y.-R. Wang, and Y.-F. Liao, Tone recognition of continuous Mandarin speech based on tone nucleus model and neural network, IEICE Technical Report, NLC2006-47, SP2006-103, pp.107-112.
54. J.-S. Zhang, M. Fujimoto, W. Herbordt and, "Speech Recognition Evaluation at ATR --- Chinese Acoustic Models", Proc. of the he Acoustic Society of Japan (ASJ), 2006 Spring, March. pp.183-184.
55. Zi-Yu Xiong, Ai-Jun Li, J.-S. Zhang and S. Nakamura, "A Case Study on Rhythmic Patterns of Prosodic Phrasing Using ATR Four Regional Accented Chinese Speech Database", Proc. of the he Acoustic Society of Japan (ASJ), 2006 Spring, March., pp. 381-382.
56. J.-S. Zhang and S. Nakamura, "Mutual Information Criterion based Phoneme Set Optimization for Lexicon Building of Chinese Speech Recognition System", Proc. of the he Acoustic Society of Japan (ASJ), pp.183-184, 2005 Fall.
57. J.-S. Zhang, M. Mizumachi, F. K. Soong and, "An introduction to ATRPTH: a phonetically rich sentence set based Chinese Putonghua speech database developed by ATR", Proc. of the he Acoustic Society of Japan (ASJ), pp.167-168, 2003 Fall.
58. J.-S. Zhang, T. Matusi and S. Nakamura, "Robust Training of Japanese acoustic models from ATR phonetically balanced database", Proc. of the Acoustic Society of Japan (ASJ), pp.11-12, 2003 Spring.
59. J.-S. Zhang, S. Nakamura and K. Hirose, "Is tone recognition necessary for Chinese speech recognition—evidence from Pinyin-to-character conversion", Proc. of ASJ, Sept. 2002, pp.5-6.
60. J.-S. Zhang and S. Nakamura, "A bootstrap approach to develop statistical word segmentation system for Chinese", Proc. of ASJ, March, 2002, pp.75-76.
61. J.-S. Zhang, K. Markov, T. Matsui, R. Gruhn and S. Nakamura, "Developing robust baseline acoustic models for noisy speech recognition in SPINE2 project", Proc. of ASJ, March, 2002, pp.65-66.
62. K. Markov, T. Matsui, R. Gruhn, J.-S. Zhang and S. Nakamura, "ATR system for robust speech recognition in real world noisy and channel environments", Technical report of IEICE. SP2001-90(2001-12), pp.37-44.
63. J.-S. Zhang, K. Markov, T. Matusi and S. Nakamura, "Inter-word pauses modeling for recognizing noisy speech in SPINE2 project", Technical report of SLP, IPSJ, Vol. 2002, No. 10, pp.171-176.
64. J.-S. Zhang, and S. Nakamura, “Least-to-Most ordered search for minimum sentence set for collecting speech database”, Proc. of Fall meeting of Acoustics Society of Japan (ASJ), Oct. 2001, pp.145-146.
65. J.-S. Zhang, Sh.-W. Zhang, Y. Sagisaka, and S. Nakamura, “Chinese speech recognition based on clustered acoustic units”, Proc. of Spring meeting of Acoustics Society of Japan (ASJ), March, 2001. pp.186-187.
66. J.-S. Zhang, K. Usami, T. Matsui, and S. Nakamura, “A Design of Chinese Phonetically-balanced sentence set”, Proc. of Spring meeting of Acoustics Society of Japan (ASJ), March, 2001. pp.188-189.
67. J.-S. Zhang, Sh.-W. Zhang, Y. Sagisaka and S. Nakamura, “Modeling segmental context effect for Chinese Speech Recognition”, Information Processing Society Japan technical report, Vol.2001, No.11. pp.37-42.
68. Sh.-Wu. Zhang, J.-S. Zhang, S. Nakamura and Y. Sagisaka, “A preliminary investigation of sub-syllabic modeling for Chinese recognition based on HMnet”, Proc. of Fall meeting of Acoustics Society of Japan (ASJ), Sep. 2000.
69. J.-S. Zhang, K. Hirose, “Chinese tone nuclei detection based on sequential clustering and linear discriminant analysis”, IEICE technical report, Vol.99, No.525, Dec. 1999, pp.19-24.
70. J.-S. Zhang, K. Hirose, “Labeling tone coarticulation effects for Chinese lexical tone recognition”, Proc. of Fall meeting of Acoustics Society of Japan (ASJ), Sep. 1999, pp.1-2.
71. J.-S. Zhang, K. Hirose, “Modeling Downstep effect for Chinese lexical tone recognition”, Proc. of Fall meeting of ASJ, Sep. 1999, pp.3-4.
72. J.-S. Zhang, K. Hirose, “Modeling Contextual Tone Variations in F0 Contour for Chinese Tone Recognition”, Proc. of Spring meeting of ASJ, March, 1999, pp. 149-150.
73. J.-S. Zhang, K. Hirose, “Lexical tone recognition based on tone-critical segment”, Proc. of Spring meeting of ASJ, March, 1999, pp. 151-152.
74. J.-S. Zhang, K. Hirose, “Chinese tone recognition based on sub-syllabic F0 contours”, Proc. of Fall meeting of ASJ, Sept. 1998, pp.167-168.
75. J.-S. Zhang, B-q Dai, Z-q Yu, C-f Wang, “Study on Fuzzy Hidden Markov Modeling Techniques”, Proceedings of The Second National Conference on Man Machine Speech Communication, Guilin, China, Sept. 1992, pp.125-129.
76. J.-S. Zhang, B-q Dai, Z-q Yu, C-f Wang, “Study on Initialization of Hidden Markov Model Parameters”, Proceedings of The Second National Conference on Man Machine Speech Communication, Guilin, China, Sept. 1992, pp. 120-123.
77. Z-q Yu, B-q Dai, J.-S. Zhang, C-f Wang, “New Training Procedure of HMM Based on Fuzzy Observational Signal Sequences”, Proceedings of The Second National Conference on Man Machine Speech Communication, Guilin, China, Sept. 1992, pp. 130-133.
78. J.-S. Zhang, B-q Dai, “Continuous Speech Recognition and Understanding based on Knowledge and Fuzzy Strategy”, Proceedings of the 1st National Intelligence and Information Technology Conference, Beijing, Feb. 1992, pp.148-151.

l 专利
1. 名称：音声認識装置、自動翻訳装置、音声認識方法、プログラム、及びデータ構造
u 公开号：特許公開２００９－６９２７６
u 公開日:２００９年４月２日
u 発明者: 張 勁松 外１名
u 出願人：独立行政法人情報通信研究機構
u 出願日:２００７年９月１１日
u 出願番号:特許出願２００７－２３５３４３
2. 名称：音素単位セットを最適化する方法及びシステム
u 特許公開２００６－１２６７３０
u 公開日：２００６年５月１８日
u 発明者：張 勁松 外２名
u 出願人：株式会社国際電気通信基礎技術研究所
u 出願番号：特許出願２００４－３１８２０８
u 出願日：２００４年１１月１日
3. 名称：中国語の声調分類装置及び中国語のＦ０生成装置
u 特許公開２００５－２６５９５５
u 公開日：２００５年９月２９日
u 発明者：チョウ キンソン 外２名
u 出願人：株式会社国際電気通信基礎技術研究所
u 出願番号：特許出願２００４－７４５９４
u 出願日：２００４年３月１６日
4. 名称：音声認識システム
u 特許公開２００２－２２９５９０
u 公開日：２００２年８月１６日
u 発明者：チョウ?キンソン 外３名
u 出願人：株式会社エイ?ティ?アール音声言語通信研究所
u 出願番号：特許出願２００１－２５６１４
u 出願日：２００１年２月１日
5. 名称：音声データベース用文セットの選択方法
u 特許公開２００２－２６８６７２
u 公開日：２００２年９月２０日
u 発明者：チョウ?キンソン 外2名
u 出願人：株式会社エイ?ティ?アール音声言語通信研究所
u 出願番号：特許出願２００１－７０５６０
u 出願日：２００１年３月１３日