內(nèi)蒙古大學(xué)

內(nèi)蒙古大學(xué)計(jì)算機(jī)學(xué)院研究生導(dǎo)師張學(xué)良介紹如下：

張學(xué)良，工學(xué)博士，內(nèi)蒙古大學(xué)計(jì)算機(jī)學(xué)院教授，博士生導(dǎo)師

Engishversion

聯(lián)系方式：

E-mai:CSZX[AT]imu[dot]edu[dot]cn;   zhangxueiang[AT]imudges[dot]com.

地址：內(nèi)蒙古呼和浩特市大學(xué)西路235號(hào)，計(jì)算機(jī)學(xué)院0415

郵編：010021

個(gè)人經(jīng)歷：

1999年-2003年:內(nèi)蒙古大學(xué)，計(jì)算機(jī)學(xué)院，信息管理與信息系統(tǒng)，獲學(xué)士學(xué)位；

2003年-2005年:哈爾濱工業(yè)大學(xué)，計(jì)算機(jī)科學(xué)與技術(shù)系，人工智能與圖像處理，獲碩士學(xué)位；

2005年-2006年:中國(guó)電子科技集團(tuán)第三研究所，任助理工程師；

2006年-2010年:中國(guó)科學(xué)院自動(dòng)化研究所，模式識(shí)別國(guó)家重點(diǎn)實(shí)驗(yàn)室語音信號(hào)處理，獲博士學(xué)位；

2010年-2013年；內(nèi)蒙古大學(xué)，計(jì)算機(jī)學(xué)院講師，碩士生導(dǎo)師；

2013年-2017年；內(nèi)蒙古大學(xué)，計(jì)算機(jī)學(xué)院副教授，博士生導(dǎo)師；

2018年-至今；內(nèi)蒙古大學(xué)，計(jì)算機(jī)學(xué)院教授；

2015年-2016年:美國(guó)俄亥俄州立大學(xué)訪問學(xué)者;

研究領(lǐng)域：

語音信號(hào)處理，計(jì)算聽覺場(chǎng)景分析，語音合成，語音分離

論文：

Journa:

1.Zhong-Qiu Wang, Xueiang Zhang and Deiang Wang, "Robust Speaker ocaization Guided by Deep earning-Based Time-Frequency Masking," in IEEE/ACM Transactions on Audio, Speech, and anguage Processing, 27(1), pp. 178-188, 2019. (Top journa, CCF rank B, SCI IF 2.95).

2.Shuai Nie, Shan iang, Wenju iu, Xueiang Zhang and Jianhua Tao, "Deep earning Based Speech Separation via NMF-Stye Reconstructions," in IEEE/ACM Transactions on Audio, Speech, and anguage Processing, 26(11), pp. 2043-2055, 2018. (Top journa, CCF rank B, SCI IF 2.95).

3.ShaSha Xia, Xueiang Zhang and Shan iang,“Supervised Speech Separation Using Optima Ratio Mask,” Acta Automatica Sinica, 44(10): 1876-1887, 2018. (in Chinese).

4.Xueiang Zhang and Deiang Wang, “Deep earning Based Binaura Speech Separation in Reverberant Environments,” IEEE/ACM Trans Audio, Speech and anguage Processing 25(5): 1075-1084, 2017. (Top journa, CCF rank B, SCI IF 2.95).

5.張暉，蘇紅，張學(xué)良，高光來，《基于卷積神經(jīng)網(wǎng)絡(luò)的魯棒性基音檢測(cè)方法》，自動(dòng)化學(xué)報(bào)，42(6):959-964，2016.

6.聶帥，劉文舉，梁山，張學(xué)良，《基于深度學(xué)習(xí)語音分離技術(shù)的研究現(xiàn)狀與進(jìn)展》，自動(dòng)化學(xué)報(bào)，42(6):814-833，2016.

7.Xueiang Zhang, Hui Zhang, Shuai Nie, Guangai Gao and Wenju iu. "A Pairwise Agorithm Using Deep Stacking Network for Speech Separation and Pitch Estimation," IEEE/ACM Trans. Audio, Speech and anguage Processing 24(6): 1066-1078, 2016 (Top journa, CCF rank B, SCI IF 2.95).

8.Wenju iu, Xueiang Zhang, Wei Jiang, et a. “Monaura Voiced Speech Segregation Based On Eaborate Harmonic Grouping Strategies”. Science China Information Sciences, 2011, 54(12): 2471-2480.

9.Xueiang Zhang, Wenju iu and Bo Xu, “Monaura Voiced Speech Segregation Based On Dynamic Harmonic Function”, In EURASIP Journa On Audio, Speech, And Music Processing, Voume 2010, Artice ID 252374, 13 Pages, 2010

10.張學(xué)良，劉文舉，李鵬，徐波，《改進(jìn)諧波組織規(guī)則的單通道濁語音分離系統(tǒng)》，聲學(xué)學(xué)報(bào)，36(1):89-96，2011.

Conference:

1.Ke Tan, Xueiang Zhang and Deiang Wang, "Rea-time Speech Enhancement using an Efficient Convoutiona Recurrent Network for Dua-Microphone Mobie Phones in Cose-tak Scenarios," ICASSP 2019, Brighton, UK. (Top conference, CCF rank B)

2.Fei Zhao, Hao i and Xueiang Zhang, "A Robust Text-Independent Speaker Verification Method based on Speech Separation and Deep Speaker," ICASSP 2019, Brighton, UK. (Top conference, CCF rank B)

3.Yun iu, Hui Zhang, Xueiang Zhang and inju Yang, "Supervised Speech Enhancement with Rea Spectrum Approximation," ICASSP 2019, Brighton, UK. (Top conference, CCF rank B)

4.Jingdong i, Hui Zhang, Rui iu, Xueiang Zhang and ong Fei, "End-to-End Mongoian Text-to-Speech System," ISCSP 2018, Taipei, Taiwan.

5.Yun iu, Hui Zhang, and Xueiang Zhang, "Using Shifted Rea Spectrum Mask as Training Target for Supervised Speech Separation," INTERSPEECH 2018, Hyderabad, India. (Top conference, CCF rank C).

6.Zhong-Qiu Wang, Xueiang Zhang and Deiang Wang, "Robust TDOA Estimation Based on Time-Frequency Masking and Deep Neura Networks", INTERSPEECH 2018, Hyderabad, India. (Top conference, CCF rank C).

7.Hui Zhang, Xueiang Zhang and Guangai Gao, "Training Supervised Speech Separation System to Improve STOI and PESQ Directy," ICASSP 2018，Cagary, Aberta, Canada. (Top conference, CCF rank B).

8.Qingong i, Xueiang Zhang and Hao i, "Onine Direction of Arriva Estimation Based on Deep earning," ICASSP 2018, Cagary, Aberta, Canada. (Top conference, CCF rank B).

9.Shasha Xia, Hao i and Xueiang Zhang, "Using Optima Ratio Mask as Training Target for Supervised Speech Separation", APSIPA ASC 2017, Kuaa umpur, Maasiya.

10.Xueiang Zhang and Deiang Wang, “Binaura Reverberant Speech Separation Based on Deep Neura Networks,” INTERSPEECH 2017, Stockhom, Sweden. (Top conference, CCF rank C).

11.Hui Zhang, Xueiang Zhang and Guangai Gao, "Muti-target Ensembe earning for Monaura Speech Separation," INTERSPEECH 2017, Stockhom, Sweden. (Top conference, CCF rank C).

12.Xueiang Zhang, Zhong-Qiu Wang and Deiang Wang, "A speech enhancement agorithm by iterating singe- and muti-microphone processing and its appication to robust ASR," ICASSP 2017, New Oreans, USA. (Top conference, CCF rank B).

13.Hui Zhang, Xueiang Zhang and Guangai Gao, "Muti-channe Speech Enhancement Based on Deep Stacking Network," Speech Processing in Everyday Environments (CHiME 2016).

14.Hao i, Shuai Nie, Xueiang Zhang and Hui Zhang, "Jointy Optimizing Activation Coefficients of Convoutive NMF Using DNN for Speech Separation," INTERSPEECH 2016, San Francisco, USA. (Top conference, CCF rank C).

15.Hong Su, Hui Zhang, Xueiang Zhang and Guangai Gao. "Convoutiona Neura Network for Robust Pitch Determination," ICASSP 2016, Shanghai, China. (Top conference, CCF rank B).

16.Shuai Nie, Shan iang, Hao i, Xueiang Zhang, et a. "Expoiting Spectro-Tempora Structures Using NMF For DNN-Based Supervised Speech Separation," ICASSP 2016, Shanghai, China. (Top conference, CCF rank B).

17.Shuai Nie, Shan iang, Wei Xue, Xueiang Zhang, et a. "Two-Stage Muti-Target Joint earning for Monaura Speech Separation," INTERSPEECH 2015, Dresden, Germany. (Top conference, CCF rank C).

18.Shuai Nie, Wei Xue, Shan iang, Xueiang Zhang, et a. "Joint Optimization of Recurrent Networks Expoiting Source Auto-Regression for Source Separation", INTERSPEECH 2015, Dresden, Germany. (Top conference, CCF rank C).

19.Hui Zhang, Xueiang Zhang and Guangai Gao, "Document Summarization Based on Semantic Representations," IAP 2015, Guangzhou, China.

20.Hui Zhang, Xueiang Zhang, Shuai Nie, et a. "A Pariwise Agorithm for Pitch Estimation and Speech Separation Using Deep Stacking Network", ICASSP 2015, Brisbane, Austraia. (Top conference, CCF rank B).

21.Shuai Nie, Hui Zhang, Xueiang Zhang and Wenju iu, "Deep Stacking Networks with Time Series for Speech Separation", ICASSP 2014, Forence, Itay. (Top conference, CCF rank B).

22.Xueiang Zhang, Hui Zhang and Guangai Gao, "Missing Feature Reconstruction Methods For Robust Speaker Identification," EUSIPCO 2014, isbon, Portuga.

23.Xueiang Zhang and Wenju iu, "Monaura Voiced Speech Segregation Based on Pitch and Comb Fiter," INTERSPEECH 2011, Forence, Itay. (Top conference, CCF rank C).

24.Xueiang Zhang, Wenju iu, Peng i and Bo Xu, "Monaura Voiced Speech Segregation Based On Eaborate Harmonic Grouping Strategy," ICASSP 2009, Taipei, Taiwan. (Top conference, CCF rank B).

25.Xueiang Zhang, Wenju iu, Peng i and Bo Xu, "Mutipitch Detection Based On Weighted Summary Correogram," ISCSP 2008, Kunming, China.

26.Xueiang Zhang, Wenju iu and Bo Xu, "Muti-Pitch Determination Agorithm Based On Mixture apacian Distribution," ICAIP 2010, Shanghai, China.

主持或參與項(xiàng)目：

主持，知識(shí)引導(dǎo)的深度學(xué)習(xí)語音降噪研究，國(guó)家自然科學(xué)基金，2019.1-2022.12

主持，計(jì)算聽覺場(chǎng)景分析中基于統(tǒng)計(jì)模型的聽覺片段切分研究，國(guó)家自然科學(xué)基金，2014.1-2017.12

主持，蒙古語音合成系統(tǒng)，內(nèi)蒙古大學(xué)高層次人才引進(jìn)科研啟動(dòng)項(xiàng)目，2010.12-2013.12

主持，基于訓(xùn)練模型的蒙古語語音合成研究，自治區(qū)自然科學(xué)基金，2011.10-2014.10

參與，音頻場(chǎng)景分析，國(guó)家重點(diǎn)基礎(chǔ)研究發(fā)展計(jì)劃（973計(jì)劃），2005.1-2009.1

參與，基于客觀質(zhì)量評(píng)估和音頻場(chǎng)景分析語音分離新方法研究，國(guó)家自然基金委重大研究計(jì)劃，2008.1-2011.1

參與，智能與蒙文信息處理，內(nèi)蒙古大學(xué)科技創(chuàng)新團(tuán)隊(duì)建設(shè)計(jì)劃

（歡迎有志從事語音信號(hào)處理的同學(xué)報(bào)考碩士或者博士研究生）

畢業(yè)/在讀學(xué)生:

丁祺（2011-2014），基于隱馬爾可夫的石油管道檢測(cè)(IBM)

李婷慧（2012-2014），蒙古文韻律預(yù)測(cè)算法研究

康征（2013-2015），基于深度神經(jīng)網(wǎng)絡(luò)語音識(shí)別

蘇紅（2013-2016），噪聲環(huán)境下基音提取(北京小桔科技有限公司，滴滴出行)

彭曉騰（2013-2016），聽覺感知評(píng)估方法

石博天（2014-2016），深度神經(jīng)網(wǎng)絡(luò)，語音分離(北京理工大學(xué))

李歡（2014-2016），說話人識(shí)別

郭亞娜（2014-2016），深度神經(jīng)網(wǎng)絡(luò)在語音識(shí)別中的應(yīng)用

李號(hào)（2014-2017），麥克風(fēng)陣列技術(shù)

夏莎莎（2014-2017），大規(guī)模數(shù)據(jù)語音分離

楊冰晴（2015-2017），語音分離

張子慧（2015-2018），說話人識(shí)別

李慶龍（2015-2018），聲源定位(北京云知聲信息技術(shù)有限公司)

王思蒙（2015-2018），語音端點(diǎn)檢測(cè)（工商銀行山東省分行）

李光鵬（2016-2018），語音分離算法DSP實(shí)現(xiàn)（招商銀行濟(jì)南分行）

毛振蘇（2016-2018），單通道語音分離

在讀：

劉允（2016-），單通道語音分離

趙飛（2016-），魯棒性說話人識(shí)別

李號(hào)（博士生）（2017-），麥克風(fēng)陣列技術(shù)

李勁東（2017-），語音合成

許天驕（2017-），多通道語音分離

谷悅（2017-），語音關(guān)鍵詞檢測(cè)

劉樂（2017-），單通道語音分離

張成剛（博士生）（2018-），

張鵬（2018-），

王心恬（2018-），

劉晉江（2018-），

王志杰（2018-），

學(xué)術(shù)任職：

國(guó)家自然基金通訊評(píng)審，INTERSPEECH, ACM/IEEE Transaction on Audio, Speech and anguage Processing，Journa of Seected Topics in Signa Processing, Speech Communication, EURASIP Journa on Audio, Speech, and Music Processing, Computationa Inteigence and Neuroscience審稿人，中國(guó)計(jì)算機(jī)學(xué)會(huì)（CCF）語音對(duì)話與聽覺專業(yè)組委員。