Research

Publication List: Paper (Fiscal Year 2015: April/2015-March/2016)

• Scientific Journals [Peer Reviewed]
  
  
  
  • Hiroki Tanaka, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura．
    "NOCOA+: Multimodal Computer-Based Training for Social and Communication Skills"
    IEICE Transactions on Information and Systems, E98-D-8, pp.1536-1544, August 2015.
  • Philip Arthur, Graham Neubig, Sakriani Sakti, Tomoki Toda and Satoshi Nakamura.
    “Semantic Parsing of Ambiguous Input through Paraphrasing and Verification”
    Transactions of the Association for Computational Linguistics (TACL), vol.3, pp571-584, Dec. 2015
  • Masahiro Mizukami, Lasguido Nio, Hideaki Kizuki, Toshio Nomura, Graham Neubig, Koichiro Yoshino, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "Example Based Dialogue System Based on Satisfaction Prediction"
    Japanese Society for Artificial Intelligence Vol. 31(2016) No. 1, Jan, 2016.
  • Graham Neubig, Taro Watanabe.
    "Optimization for Statistical Machine Translation: A Survey"
    Computational Linguistics, 42-1, pp.1--54. March 2016.
• International Conference [Peer Reviewed]
  
  
  
  • Hiroki Tanaka, Sakriani Sakti, Graham Neubig, Tomoki Toda, Hideki Negoro, Hidemi Iwasaka, Satoshi Nakamura,
    "Automated Social Skills Trainer",
    International Conference on Intelligent User Interfaces (IUI), pp.17-27, Atlanta, Mar. 2015.
  • Shinnosuke Takamichi, Tomoki Toda, Alan W. Black, Satoshi Nakamura,
    "Parameter generation algorithm considering modulation spectrum for HMM-based speech synthesis",
    Proceedings of ICASSP, page4210-4214, 2015
  • Shinnosuke Takamichi, Tomoki Toda, Alan W. Black, Satoshi Nakamura,
    "Modulation Spectrum-Constrained Trajectory Training for GMM-Based Voice Conversion"
    Proceedings of ICASSP, page4859-4863, 2015
  • Hayato Maki, Tomoki Toda, Sakriani Sakti, Graham Neubig, Satoshi Nakamura,
    "EEG Signal Enhancement using Multichannel Wiener Filter with a Spatial Correlation Prior"
    Proceedings of ICASSP, page2639-2643, 2015
  • Quoc Truong Do, Satoshi Nakamura, Marc Delcroix, Takaaki Hori,
    "WFST-BASED STRUCTURAL CLASSIFICATION INTEGRATING DNN ACOUSTIC FEATURES AND RNN LANGUAGE FEATURES FOR SPEECH RECOGNITION",
    Proceedings of ICASSP, page4959-4963, 2015
  • Andros Tjandra, Sakriani Sakti, Graham Neubig, Tomoki Toda, Mirna Adriani, Satoshi Nakamura,
    "COMBINATION OF TWO-DIMENSIONAL COCHLEOGRAM AND SPECTROGRAM FEATURES FOR DEEP LEARNING-BASED ASR",
    Proceedings of ICASSP, page4525-4529, 2015
  • Yuki Murota, Daichi Kitamura, Shoichi Koyama, Hiroshi Saruwatari, Satoshi Nakamura,
    "STATISTICAL MODELING OF BINAURAL SIGNAL AND ITS APPLICATION TO BINAURAL SOURCE SEPARATION",
    Proceedings of ICASSP, page494-498, 2015
  • Yusuke Oda, Graham Neubig, Sakriani Sakti, Tomoki Toda, and Satoshi Nakamura,
    "Ckylark: A More Robust PCFG-LA Parser."
    In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Demonstrations, pp.41-45,Denver, CO, USA, June, 2015.
  • Graham Neubig, Philip Arthur, and Kevin Duh.
    "Multi-Target Machine Translation with Multi-Synchronous Context-free Grammars."
    In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies (HLT), pp.293-302, Denver, CO, USA, June, 2015.
  • Yusuke Oda, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "Syntax-based Simultaneous Translation through Prediction of Unseen Syntactic Constituents"
    The 53rd Annual Meeting of the Association for Computational Linguistics (ACL) Long Paper Track. pp. 198-207. July 2015.
  • Akiva Miura, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "Improving Pivot Translation by Remembering the Pivot"
    The 53rd Annual Meeting of the Association for Computational Linguistics (ACL) Short Paper Track. pp. 573-577. July 2015.
  • Shinnosuke Takamichi, Kazuhiro Kobayashi, Kou Tanaka, Tomoki Toda,Satoshi Nakamura,
    "The NAIST Text-to-Speech System for the Blizzard Challenge 2015,"
    Proc. Blizzard Challenge, Berlin, Germany, Sep., 2015.
  • Takuya Hiraoka, Kallirroi Georgila, Elnaz Nouri, David Traum, Satoshi Nakamura,
    "Reinforcement Learning in Multi-Party Trading Dialog,"
    The 16th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL), Czech, Sep., 2015.
  • Takashi Mieno, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura,
    "Speed or Accuracy? A Study in Evaluation of Simultaneous Speech Translation."
    Proc. INTERSPEECH, pp. 2267-2271, Germany, Sep. 2015.
  • Shinnosuke Takamichi, Tomoki Toda, Alan W. Black, Satoshi Nakamura,
    "Modulation Spectrum-Constrained Trajectory Training Algorithm for HMM-Based Speech Synthesis,"
    Proc. INTERSPEECH, pp. 1206-1210, Germany, Sep. 2015.
  • Yuji Oshima, Shinnosuke Takamichi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "Non-native Speech Synthesis Preserving Speaker Individuality based on Partial Correction of Prosodic and Phonetic Characteristics,"
    Proc. INTERSPEECH, pp. 299-303, Germany, Sep. 2015.
  • Kazuhiro Kobayashi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "Non-native Speech Synthesis Preserving Speaker Individuality based on Partial Correction of Prosodic and Phonetic Characteristics,"
    Proc. INTERSPEECH, pp. 299-303, Germany, Sep. 2015.
  • Kazuhiro Kobayashi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "Statistical Singing Voice Conversion based on Direct Waveform Modification with Global Variance,"
    Proc. INTERSPEECH, pp. 2754-2758, Germany, Sep. 2015.
  • Quoc Truong Do, Shinnosuke Takamichi, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura,
    "Preserving Word-level Emphasis in Speech-to-speech Translation using Linear Regression HSMMs,"
    Proc. INTERSPEECH, pp. 3665-3669, Germany, Sep. 2015.
  • Yusuke Tajiri, Kou Tanaka, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "Non-Audible Murmur Enhancement based on Statistical Conversion using Air- and Body-Conductive Microphones in Noisy Environments,"
    Proc. INTERSPEECH, pp. 2769-2773, Germany, Sep. 2015.
  • Patrick Lumban Tobing, Kazuhiro Kobayashi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "Articulatory Controllable Speech Modification based on Gaussian Mixture Models with Direct Waveform Modification using Spectrum Differential,"
    Proc. INTERSPEECH, pp. 3350-3354, Germany, Sep. 2015.
  • The Tung Nguyen, Graham Neubig, Hiroyuki Shindo, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura,
    "A Latent Variable Model for Joint Pause Prediction and Dependency Parsing",
    Proc. INTERSPEECH, pp. 2719-2723, Germany, Sep. 2015.
  • Yuri Nishigaki, Shinnosuke Takamichi, Tomoki Toda, Graham Neubig, Sakti Sakriani, Satoshi Nakamura,
    "Prosody-Controllable HMM-Based Speech Synthesis Using Speech Input,"
    Proc. of 2015 First International Workshop on MLSLP, Aizu, Japan, Sep., 2015.
  • Kyoshiro Sugiyama, Masahiro Mizukami, Graham Neubig, Koichiro Yoshino, Sakriani Sakti, Tomoki Toda and Satoshi Nakamura,
    "An Investigation of Machine Translation Evaluation Metrics in Cross-lingual Question Answering,"
    Proc. of WMT, pp.442--449, Sep. 2015.
  • Hayato Maki, Tomoki Toda, Sakriani Sakti, Graham Neubig, Satoshi Nakamura,
    "An Evaluation of EEG Ocular Artifact Removal with a Multi-channel Wiener Filter Based on Probabilistic Generative Model,"
    Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, August, 2015.
  • Jingyi Zhang, Masao Utiyama, Eiichro Sumita, Graham Neubig, Satoshi Nakamura,
    "A Binarized Neural Network Joint Model for Machine Translation,"
    Proc. EMNLP, pp. 2094--2099, Portugal, Sep. 2015.
  • Kou Tanaka, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "An Enhanced Electrolarynx with Automatic Fundamental Frequency Control based on Statistical Prediction,"
    The 17th International ACM SIGACCESS Conference on Computers & Accessibility, pp. 435-436, Oct. 2015.
  • Satoshi Nakamura,
    "Toward Simultaneous and Natural Speech-to-Speech Translation," [invited]
    The 13th National Conference on Man-Machine Speech Communication (NCMMSC 2015), Tianjin, China, October, 2015.
  • Satoshi Nakamura,
    "Toward Simultaneous, Natural and Multimodal Speech-to-Speech Translation," [invited]
    18th Oriental COCOSDA 2015, Shanghai, China, October, 2015.
  • Nurul Lubis, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura,
    "Construction and Analysis of Social-Affective Interaction Corpus in English and Indonesian,"
    Proceedings of the 18th Oriental COCOSDA, pp. 202--206, Shanghai, China, October, 2015.
  • Hiroyuki Fudaba,Yusuke Oda,Koichi Akabe,Graham Neubig,Hideaki Hata,Sakriani Sakti,Tomoki Toda,Satoshi Nakamura,
    "Pseudogen: a Tool to Automatically Generate Pseudo-Code from Source Code,"
    30th IEEE/ACM International Conference on Automated Software Engineering Tool Demonstration，Lincoln，2015.11.
  • Yusuke Oda,Hiroyuki Fudaba,Graham Neubig,Hideaki Hata,Sakriani Sakti,Tomoki Toda,Satoshi Nakamura,
    "Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation,"
    30th IEEE/ACM International Conference on Automated Software Engineering，Lincoln，2015.11.
  • Sakriani Sakti, Oyunchimeg Shagdar, Fawzi Nashashibi, Satoshi Nakamura,
    "Context Awareness and Priority Control for ITS based on Automatic Speech Recognition,"
    Proc. of 2015 14th International Conference on ITS Telecommunications (ITST), December 2015.
  • Makoto Morishita, Koichi Akabe, Yuto Hatakoshi, Graham Neubig, Koichiro Yoshino, Satoshi Nakamura,
    "Parser Self-Training for Syntax-Based Machine Translation,"
    12th International Workshop on Spoken Language Translation (IWSLT). December 2015.
  • Quoc Truong Do, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura,
    "Improving Translation of Emphasis with Pause Prediction in Speech-to-speech Translation Systems,"
    12th International Workshop on Spoken Language Translation (IWSLT). December 2015.
  • Michael Heck, Quoc Truong Do, Sakriani Sakti, Graham Neubig, Satoshi Nakamura,
    "The NAIST English Speech Recognition System for IWSLT 2015,"
    12th International Workshop on Spoken Language Translation (IWSLT). December 2015.
  • Oliver Adams, Graham Neubig, Trevor Cohn, Steven Bird.
    "Inducing Bilingual Lexicons from Small Quantities of Sentence-Aligned,"
    12th International Workshop on Spoken Language Translation (IWSLT). December 2015.
  • Hiromitsu Ohara, Yu Suzuki, Akiyo Nadamoto,
    "Detection of Missing Tweets based on Browsing Interval and Topic Granularity,"
    Proceedings of iiWAS2015, pp.206-214, Dec. 2015.
  • Quoc Truong Do, Michael Heck, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura,
    "The NAIST ASR System for the 2015 Multi-Genre Broadcast Challenge: On Combination of Deep Learning Systems Using A Rank-Score Function,"
    Proc. of 2015 IEEE ASRU, December 2015.
  • Sakriani Sakti, Faiz Ilham, Graham Neubig, Tomoki Toda, Ayu Purwarianti, Satoshi Nakamura,
    "Incremental Sentence Compression Using LSTM Recurrent Networks,"
    Proc. of 2015 IEEE ASRU, December 2015.
  • Nurul Lubis, Sakriani Sakti, Graham Neubig, Koichiro Yoshino, Tomoki Toda, Satoshi Nakamura,
    "A Study of Social-Affective Communication: Automatic Prediction of Emotion Triggers and Responses in Television Talk Shows,"
    Proc. of 2015 IEEE ASRU, December 2015.
  • Masahiro Mizukami, Hideaki Kizuki, Toshio Nomura, Graham Neubig, Koichiro Yoshino, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura
    "Adaptive Selection from Multiple Response Candidates In Example-Based Dialogue,"
    Proc. of 2015 IEEE ASRU, December 2015.
  • Andros Tjandra, Sakriani Sakti, Satoshi Nakamura, Mirna Adriani,
    "Stochastic Gradient Variational Bayes for Deep Learning-Based ASR,"
    Proc. of 2015 IEEE ASRU, December 2015.
  • Yuiko Tsunomori, Graham Neubig, Takuya Hiraoka, Masahiro Mizukami, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura,
    "A Dialog System to Detect Deception,"
    7th International Workshop on Spoken Dialog Systems (IWSDS), January 2016.
  • Takuya Hiraoka, Graham Neubig, Koichiro Yoshino, Tomoki Toda, Satoshi Nakamura,
    "Active Learning for Example-based Dialog Systems,"
    7th International Workshop on Spoken Dialog Systems (IWSDS), January 2016.
  • Koichiro Yoshino, Takuya Hiraoka, Graham Neubig, Satoshi Nakamura,
    "Dialogue State Tracking using Long Short Term Memory Neural Networks,"
    7th International Workshop on Spoken Dialog Systems (IWSDS), January 2016.
  • Soichi Yamane, Kazuhiro Kobayashi, Tomoki Toda, Tomoyasu Nakano, Masataka Goto, Satoshi Nakamura,
    "AN ESTIMATION METHOD OF VOICE TIMBRE EVALUATION VALUES USING FEATUREEXTRACTION WITH GAUSSIAN MIXTURE MODEL BASED ON REFERENCE SINGER,"
    Proc. ICASSP, pp 5265--5269, Mar. 2016.
  • Kou Tanaka, Hirokazu Kameoka, Tomoki Toda, and Satoshi Nakamura,
    "STATISTICALF0PREDICTION FOR ELECTROLARYNGEAL SPEECH ENHANCEMENTCONSIDERING GENERATIVE PROCESS OFF0CONTOURS WITHIN PRODUCT OFEXPERTS FRAMEWORK,"
    Proc. ICASSP, pp 5665--5669, Mar. 2016.
  • Kazuhiro Kobayashi, Tomoki Toda, Satoshi Nakamura,
    "IMPLEMENTATION OF F0 TRANSFORMATION FOR STATISTICAL SINGING VOICECONVERSION BASED ON DIRECT WAVEFORM MODIFICATION,"
    Proc. ICASSP, pp 5670--5674, Mar. 2016.
  • Yusuke Tajiri, Tomoki Toda, Satoshi Nakamura,
    "NOISE SUPPRESSION METHOD FOR BODY-CONDUCTED SOFT SPEECHE NHANCEMENT BASED ON EXTERNAL NOISE MONITORING,"
    Proc. ICASSP, pp 5935--5939, Mar. 2016.
• International Conference [Without Peer Review]
  
  
  
  • Graham Neubig, Makoto Morishita, Satoshi Nakamura,
    "Neural Reranking Improves Subjective Quality of Machine Translation: NAIST at WAT2015,"
    Proceedings of the 2nd Workshop on Asian Translation (WAT2015). October 2015.
  • Toshiaki Nakazawa, Hideya Mino, Isao Goto, Graham Neubig, Sadao Kurohashi and Eiichiro Sumita,
    "Overview of the 2nd Workshop on Asian Translation,"
    Proceedings of the 2nd Workshop on Asian Translation (WAT2015), pp.1-28, October 2015.
• Research Report
  
  
  
  • [In Japanese]Shinnosuke Takamichi, Tomoki Toda, Alan W. Black, Satoshi Nakamura,
    "統計的パラメトリック音声合成のための変調スペクトルに基づく音質改善法,"
    Sig-Reports, 2015-MUS-107, No. 71, pp. 1-4, May. 2015.
    (2015年度 音楽情報科学研究会 学生賞)
  • [In Japanese]Masahiro Mizukami, Nio Lasguido, Hideaki Kizuki, Toshio Nomura, Neubig Graham, Sakti Sakriani, Tomoki Toda, Satoshi Naramura,
    "用例ベース対話システムにおける用例の評価値推定,"
    JSAI2015. Hokkaido. May 2015.
  • [In Japanese]Yusuke Tajiri, Kou Tanaka, Toda Tomoki, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "Non-Audible Murmur Enhancement Method using Air- and Body-Conductive Microphones in Noisy Environments and its Evaluation,"
    IEICE Tech. Rep, Vol. 45, No. 4, SP2015-11, pp. 263-268, Jun. 2015.
  • [In Japanese]Kou Tanaka, Toda Tomoki, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "Implementation of Direct F0 Control of an Electrolarynx based on Real-time Excitation Prediction,"
    IEICE Tech. Rep, Vol. 45, No. 4, SP2015-9, pp. 251-256, Jun. 2015.
  • [In Japanese]Satoshi Tsujioka, Liang Lu (Edinburgh), Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura,
    "Acoustic Data-driven Pronunciation Lexicon for Non-native Speech Recognition,"
    IEICE, Vol. 115, No. 146 SP2015-36, pp.1-6, Jul. 2015.
  • [In Japanese]Kohei Mukaihara, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura,
    "Bottleneck Features for Emotional Speech Recognition,"
    SLP, Vol. 107, No. 2, pp.1-6, Jul. 2015.
  • [In Japanese]Akiva Miura, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura,
    "中間言語モデルを用いたピボット翻訳の精度向上"
    IPSJ-SIGNL, Vol. 2015-NL-222 No. 2, July. 2015.
  • [In Japanese]Hiroyuki Fudaba，Yusuke Oda，Graham Neubig，Koichiro Yoshino，Satoshi Nakamura．
    "統計的機械翻訳による自然言語からソースコードへの変換に関する検討"
    YANS 2015，2015.9.
    (NLP若手の会2015年奨励賞)
  • [In Japanese]Makoto Morishita, Koichi Akabe, Graham Neubig, Koichiro Yoshino, Satoshi Nakamura
    "機械翻訳の精度を考慮した構文解析器の自己学習"
    IPSJ-SIGNL 223, Hiroshima, Sep, 2015.
  • [In Japanese]Kyoshiro Sugiyama, Masahiro Mizukami, Graham Neubig, Koichiro Yoshino, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura
    "言語横断質問応答に適した機械翻訳評価尺度の検討"
    IPSJ-SIGNL 223, Hiroshima, Sep, 2015.
  • Satoshi Nakamura.
    "Knowledge Infrastructure and Collaboration for Intelligent Smart Life"
    Joint Workshop on Sustainable Cities, Quebec Government and Kyoto Prefecture, Oct. 2015.
  • [In Japanese]Soichi Yamane, Kazuhiro Kobayashi, Tomoki Toda, Tomoyasu Nakano, Masataka Goto, Graham Neubig, Sakti Sakriani, Satoshi Nakamura,
    "歌声合成システムの音源データ検索のための.声質評価値推定法"
    IPSJSIG, Vol. 2015-MUS-108, No. 6, pp. 1-6, Sep. 2015.
  • [In Japanese]Hiroki Tanaka, Sakti Sakriani, Neubig Graham, Hideki Negoro, Hidemi Iwasaka, Satoshi Nakamura
    "Automated Communication Training System with Multimodal information"
    IEICE Technical Report, SP2015-67, pp.45-50, Oct. 2015.
  • [In Japanese]Kazuhiro KOBAYASHI, Tomoki TODA, and Satoshi NAKAMURA
    "Statistical singing voice conversion based on direct waveform modification and its parameter generation algorithms"
    information IEICE Technical Report, SP2015-60, pp.7-12, Oct. 2015.
  • [In Japanese]Takafumi Sasakura, Sakriani Sakti, Hayato Maki, Graham Neubig, Tomoki Toda, Satoshi Nakamura.
    "EEGを用いた未知語知覚の検出"
    SSRW2015, No. 8, Oct. 2015.
  • [In Japanese]Yusuke Tajiri, Tomoki Toda, Satoshi Nakamura.
    "雑音環境下におけるサイレント音声通話の実現に向けた非可聴つぶやきに対する2チャネル雑音抑圧法"
    SSRW2015, No. 9, Oct. 2015.
  • [In Japanese]Yuiko Tsunomori,Graham Neubig,Sakriani Sakti,Takuya Hiraoka,Masahiro Mizukami,Tomoki Toda,Satoshi Nakamura.
    "A Dialogue SYstem to Detect Deception"
    人工知能学会研究会資料，SIG-SLUD-B502，pp. 16-20，Oct，2015.
  • [In Japanese]Masahiro Mizukami,Kyoshiro Sugiyama,Graham Neubig,Koichiro Yoshino,Sakriani Sakti,Satoshi Nakamura.
    "Construction of RNN-based Dialogue Breakdown Detector"
    人工知能学会研究会資料，SIG-SLUD-B502，pp. 16-20，Oct，2015.
  • [In Japanese]Masahiro Mizukami,Lasguido Nio,Graham Neubig,Koichiro Yoshino,Sakriani Sakti,Tomoki Toda,Satoshi Nakamura.
    "Example based Dialogue System based on Satisfaction Prediction"
    人工知能学会研究会資料，SIG-SLUD-B502，pp. 16-20，Oct，2015.
  • [In Japanese]Yusuke Tajiri, Tomoki Toda, Satoshi Nakamura.
    "Noise Suppression Method for Body-Conducted Soft Speech based on External Noise Monitoring"
    IEICE Tech. Rep, Vol. 115, No. 302, EA2015-31, pp. 41-46, Nov. 2015.
  • [In Japanese]Wakana Maeda, Yu Suzuki, Koichiro Yoshino, Satoshi Nakamura.
    "ソーシャルメディアにおける非構造化テキストデータの k-匿名化によるプライバシー保護"
    研究報告データベースシステム (DBS), 2015(22), 1-8.
    (Student Award)
  • [In Japanese]Satoshi Tsujioka, Sakriani Sakti, Graham Neubig, Koichiro Yoshino, Satoshi Nakamura.
    "Non-native ASR Utilizing Acoustice Data-driven Pronunciation Learning with Zero Knowledge of Non-native Pronunciation"
    IPSJ-SIG Technical Report, Vol. 2015-SLP-109, No.14, pp. 1-6, Dec. 2015.
  • [In Japanese]Kohei Mukaihara, Sakriani Sakti, Koichiro Yoshino,Graham Neubig, Satoshi Nakamura.
    "Exploring CNN and DNN Bottleneck Features for Emotional Speech Recognition"
    IPSJ-SIG Technical Report, Vol. 2015-SLP-109, No.15, pp. 1-6, Dec. 2015.
  • [In Japanese]Yoko Ishikawa, Takuya Hiraoka, Masahiro Mizukami, Koichiro Yoshino, Graham Neubig, Satoshi Nakamura.
    "対話状態推定のための外部知識ベースを利用した意味的素性の提案"
    IPSJ-SIG Technical Report, Vol. 2015-SLP-109, No.13, pp. 1-4, Dec. 2015.
    (Student Poster Award)
  • [In Japanese]Shinya Kura, Shinnosuke Takamichi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura.
    "音声波形加工に基づく非母語音声の継続長補正法の評価と分析"
    IPSJ-SIG Technical Report, Vol. SP2015-73, No. 4, pp. 19-24, Dec. 2015.
  • [In Japanese]Shinnosuke Takamichi, Keita Higuchi, Satoshi Nakamura.
    "音声合成技術を用いたアバターへのアイデンティティ投影"
    WISS2015, 1-R-16, Dec., 2015.
  • [In Japanese]Akiva Miura, Graham Neubig, Michael Paul, Satoshi Nakamura.
    "構文木と句の極大性に基づく機械翻訳のための能動学習"
    IPSJ-SIGNL, Vol. 2015-NL-224 No. 19, December. 2015.
  • [In Japanese]Ikuo Keshi, Yu Suzuki, Koichiro Yoshino, Kazuto Ohara, Toshiroh Mukai, Satoshi Nakamura.
    "単語・パラグラフの分散表現を用いたTwitterからの日本語評判情報抽出"
    The 8th Forum on Data Engineering and Information Management (A1-3), 2016.
    (Student Presentation Award)
  • [In Japanese]Graham Neubig.
    "ニューラルネットに基づく機械翻訳 [招待講演]"
    AAMT/Japio Special Interest Group on Patent Translation, Mar. 2016.
  • [In Japanese]Kazuhiro Kobayashi, Tomoki Toda, Satoshi Nakamura.
    "An evaluation of F0 transformation for statistical singing voice conversion based on spectral differential filtering,"
    IEICE Tech. Rep, Vol. 115, No. 523, SP2015-113, pp. 111-116, Mar. 2016.
  • Yusuke Tajiri, Hirokazu Kameoka, Tomoki Toda, Satoshi Nakamura.
    "Nonaudible murmur enhancement based on non-negative tensor factorization of air- and body-conducted signals in real environments,"
    IEICE Tech. Rep, Vol. 115, No. 523, SP2015-114, pp. 117-122, Mar. 2016.
  • Kou Tanaka, Hirokazu Kameoka, Tomoki Toda, Satoshi Nakamura.
    "Product-of-Experts approach to integration of F0 generative process model to statistical F0 prediction for electrolaryngeal speech enhancement,"
    IEICE Tech. Rep, Vol. 115, No. 523, SP2015-161, pp. 373-377, Mar. 2016.
• Conference Presentation
  
  
  
  • Graham Neubig
    "音声翻訳技術 [招待講演],"
    No.69 JSAI Seminar, May. 2015.
  • [In Japanese]Takuya Hiraoka, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Naramura，
    "言語理解・生成部を備えた協調的説得対話システムの構築と評価,"
    JSAI2015. Hokkaido. May 2015.
  • [In Japanese]Kyoshiro Sugiyama, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Naramura,
    "知識ベースに基づく言語横断質問応答において翻訳の性能が与える影響の調査,"
    JSAI2015. Hokkaido. May 2015.
  • [In Japanese]Hiroyuki Fudaba, Yusuke Oda, Graham Neubig, Hideaki Hata, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "Supporting Learners by Automatically Generating Pseudo Code"
    Japanese Society for Information and Systems in Education, Vol. 2015, No. 1, pp. 259-260, Sept. 2015.
    (Best paper award)
  • [In Japanese]Shinnosuke Takamichi, Tomoki Toda, Masanori Morise, Satoshi Nakamura.
    "HMM音声合成における音声分析合成器STRAIGHTとWORLDの比較,"
    ASJ, pp. 271-272, Sep. 2015.
  • [In Japanese]Shinnosuke Takamichi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "HMMに基づく日本人英語音声合成における中学生徒の英語音声を用いた評価,"
    ASJ, pp. 1231-1232, Sep. 2015.
  • [In Japanese]Kazuhiro Kobayashi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "差分スペクトル補正による歌声声質変換のためのF0変換に関する検討,"
    ASJ, pp. 249-250, Sep. 2015.
  • [In Japanese]Kou Tanaka, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura.
    "統計的手法を用いた電気式人工喉頭制御における遅延時間と予測精度の調査,"
    ASJ, pp. 245-246, Sep. 2015.
  • Do Quoc Truong, Shinnosuke Takamichi, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura,
    "Study on Word-Level Emphasis Across English and Japanese,"
    ASJ, pp. 241-242, Sep. 2015.
  • [In Japanese]Yusuke Tajiri, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "外部雑音モニタリングを用いた非可聴つぶやきに対する雑音抑圧法,"
    ASJ, pp. 591-592, Sep. 2015.
  • [In Japanese]Soichi Yamane, Kazuhiro Kobayashi, Tomoki Toda, Tomoyasu Nakano, Masataka Goto, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "歌声合成による学習データ生成を利用した歌声の声質評価値推定法,"
    ASJ, pp. 247-248, Sep. 2015.
  • Patrick Lumban Tobing, Kazuhiro Kobayashi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura,
    "An Evaluation of Articulatory Controllable Speech Modication based on Gaussian Mixture Models with Direct Waveform Modication,"
    ASJ, pp. 221-222, Sep. 2015.
  • [In Japanese]Hiroki Tanaka, Sakti Sakriani, Neubig Graham, Hideki Negoro, Hidemi Iwasaka, Satoshi Nakamura.
    "Development of Automated Social Skills Trainer with Multimodal Information"
    Japanese association of social skills training，pp.61, Nov. 2015.
    (Best Presentation Award)
  • [In Japanese]Yusuke Oda, Taku Kudo, Tetsuji Nakagawa, Taro Watanabe.
    "複数の事前並べ替え候補を用いた句に基づく統計的機械翻訳"
    22nd Annual Meeting of the Association for Natural Language Processing (NLP2016). Sendai, Japan. March 2016.
    (優秀賞（言語処理学会第22回年次大会）)
  • [In Japanese]Koichiro Yoshino, Naoki Hirayama, Shinsuke Mori, Fumihiko Takahashi, Katsutoshi Itoyama, Hiroshi Okuno.
    "日本語方言における音声対訳コーパスの構築"
    22nd Annual Meeting of the Association for Natural Language Processing (NLP2016). Sendai, Japan. March 2016.
  • [In Japanese]Masahiro Mizukami, Graham Neubig, Koichiro Yoshino, Sakriani Sakti, Yu Suzuki, Satoshi Nakamura.
    "快適度推定に基づく用例ベース対話システム"
    22nd Annual Meeting of the Association for Natural Language Processing (NLP2016). Sendai, Japan. March 2016.
  • [In Japanese]Akiva Miura, Graham Neubig, Michael Paul, Satoshi Nakamura.
    "構文情報に基づく機械翻訳のための能動学習手法と人手翻訳による評価"
    22nd Annual Meeting of the Association for Natural Language Processing (NLP2016). Sendai, Japan. March 2016.
  • Philip Arthur, Graham Neubig, Sakriani Sakti, Satoshi Nakamura, Tomoki Toda.
    "Semantic Parsing of Ambiguous Input using Multi Synchronous Grammars"
    22nd Annual Meeting of the Association for Natural Language Processing (NLP2016). Sendai, Japan. March 2016.
  • The Tung Nguyen, Graham Neubig, Hiroyuki Shindo, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "A Joint Model for Pause Prediction and Dependency Parsing using Latent Variables"
    22nd Annual Meeting of the Association for Natural Language Processing (NLP2016). Sendai, Japan. March 2016.
  • [In Japanese]Makoto Morishita, Koichi Akabe, Yuto Hatakoshi, Graham Neubig, Koichiro Yoshino, Satoshi Nakamura.
    "対訳コーパスを利用した構文解析器の自己学習"
    22nd Annual Meeting of the Association for Natural Language Processing (NLP2016). Sendai, Japan. March 2016.
  • [In Japanese]Ryoya Takayama, Hiroki Tanaka, Graham Neubig, Koichiro Yoshino, Sakriani Sakti, Satoshi Nakamura.
    "ソーシャルメディアにおける語彙の豊富さと統合失調症の関係に関する考察"
    22nd Annual Meeting of the Association for Natural Language Processing (NLP2016). Sendai, Japan. March 2016.
  • [In Japanese]Hiroyuki Fudaba, Yusuke Oda, Graham Neubig, Koichiro Yoshino, Satoshi Nakamura.
    "統計的機械翻訳を用いた自然言語からのソースコード生成"
    22nd Annual Meeting of the Association for Natural Language Processing (NLP2016). Sendai, Japan. March 2016.
  • Fajri Koto(NAIST / University of Indonesia), Sakriani Sakti, Graham Neubig(NAIST), Tomoki Toda(Nagoya University / NAIST), Mirna Adriani(University of Indonesia)，Satoshi Nakamura(NAIST).
    "Automatic Detection of Memorable Spoken Quotes"
    ASJ, pp.5-6, March 2016.
  • Sakriani Sakti, Yu Odagaki, Takafumi Sasakura, Graham Neubig(NAIST), Tomoki Toda(Nagoya University/NAIST), Satoshi Nakamura(NAIST).
    “Incongruity Detection on ASR Outputs based on EEG Signals”
    ASJ, pp.83-84, March 2016.
  • [In Japanese] Hiroki Tanaka, Sakriani Sakti, Graham Neubig, Hideki Negoro, Hidemi Iwasaka, Satoshi Nakamura
    "Training Effect of Automated Social Skills Trainer with Multimodal Feedback”
    ASJ, pp. 253 – 254, Mar, 2016.
  • [In Japanese]Shinnosuke Takamichi.
    "（招待講演）私がビギナーの頃を振り返って ~20代代表として~”
    Beginners' seminar of ASJ，Mar, 2016.
  • [In Japanese]Kazuhiro Kobayashi, Tomoki Toda, Satoshi Nakamura.
    "Low Delay Statistical Singing Voice Conversion based on Direct Waveform Modification Considering Global Variance”
    ASJ, pp. 337 – 338, Mar, 2016.
  • [In Japanese]Ko Tanaka(NAIST), Hirokazu Kameoka(University of Tokyo), Tomoki Toda(Nagoya University/NAIST), Satoshi Nakamura(NAIST).
    "F0 パターン生成過程を考慮したProduct-of-Experts に基づく電気音声強調のための統計的F0 予測法”
    ASJ, pp.259-260, March 2016.
  • [In Japanese]Hayato Maki, Tomoki Toda, Sakriani Sakti, Graham Neubig, Satoshi Nakamura.
    "A Noise Reduction Method Using Spatial Prior of Event-Related Potentials”
    ASJ，pp. 627 – 628, Mar, 2016.
  • Michael Heck, Quoc Truong Do, Sakriani Sakti, Graham Neubig, Satoshi Nakamura.
    "The NAIST ASR for IWSLT: A Multi-architecture DNN System Combination Approach”
    ASJ, pp. 337 – 338, Mar, 2016.
  • Do Truong, Shinnosuke Takamichi, Sakriani Sakti, Graham Neubig(NAIST), Tomoki Toda(NAIST/Nagoya university), Satoshi Nakamura(NAIST).
    "Word-level Emphasis Transfer in Speech-to-speech Translation”
    ASJ, pp. 87 – 88, Mar, 2016.
  • [In Japanese]Seiji Kawanishi, Sakriani Sakti, Koichiro Yoshino, Graham Neubig, Satoshi Nakamura.
    "Multi-Task Deep Neural Networks for Speech and Environmental Sound Recognition”
    ASJ, pp. 163 - 164, Mar, 2016.
  • [In Japanese]Satoshi Tsujioka, Sakriani Sakti, Koichiro Yoshino, Graham Neubig, Satoshi Nakamura.
    "Non-native Automatic Speech Recognition Utilizing Acoustic Data-driven Pronunciation Learning and Acoustic Model Adaptation”
    ASJ, pp. 75 – 76, Mar, 2016.
  • [In Japanese]Kohei Mukaihara, Sakriani Sakti, Koichiro Yoshino, Graham Neubig, Satoshi Nakamura.
    "Exploring Bottleneck Features for Emotional Speech Recognition”
    ASJ, 2-1-7, Mar, 2016.
  • [In Japanese]Yusuke Tajiri, Hirokazu Kameoka, Tomoki Toda, Satoshi Nakamura.
    "A noise suppression method for body-conducted soft speech based on non-negative tensor factorization of air- and body-conducted signals”
    ASJ，pp. 557 – 558, Mar, 2016.
  • [In Japanese] Soichi Yamane, Kazuhiro Kobayashi, Tomoki Toda, Tomoyasu Nakano, Masataka Goto, Satoshi Nakamura.
    "Voice timbre control based on voice timbre evaluation values applied to voice data of singing voice synthesis system”
    ASJ, pp. 247 – 248, Mar, 2016.
  • [In Japanese] Shinya Kura, Shinnosuke Takamichi, Tomoki Toda, Graham Neubig, Satoshi Nakamura.
    "Analysis of Quality Degradation caused by Duration Correction of Non-Native Speech using Direct Waveform modification”
    ASJ, pp. 257 – 258, Mar, 2016.
  • Patrick Lumban Tobing, Tomoki Toda, Hirokazu Kameoka, and Satoshi Nakamura.
    "An Investigation of Acoustic-to-Articulatory Inversion Mapping with Latent Trajectory Gaussian Mixture Model”
    ASJ, pp. 227 – 228, Mar, 2016.
  • Nurul Lubis, Sakriani Sakti, Graham Neubig, Koichiro Yoshino, Satoshi Nakamura.
    "Predicting Emotional Responses from Spontaneous Social-Affective Interaction Data”
    ASJ, pp. 7 - 8, Mar, 2016.
  • [In Japanese]Graham Neubig.
    "プログラムを説明するプログラム [Invited talk]”
    IPSJ-ONE, Mar. 2016.
  • Satoshi Nakamura.
    "音声翻訳の歴史と概要”
    The 78th National Convention of IPSJ, Mar. 2016.
• Commentary Article & Column
  
  
  
  • Shinnosuke Takamichi, Tomoki Toda, Alan W. Black, and Satoshi Nakamura,
    "Post-Filter Using Modulation Spectrum as a Metric to Quantify Over-Smoothing Effects in Statistical Parametric Speech Synthesis,"
    APSIPA newsletter, No. 9, pp. 14-16, 2015.
  • Graham Neubig, Taku Kudo, Koichi Akabe,
    "NLP Technologies and Its Future Directions based on Error Analysis Project：3.14 Machine Translation,"
    IPSJ Magazine, Vol. 57, No. 1, pp. 36-37, Dec. 2015.
• Book
  
  
  
  • Yoh Okuno, Graham Neubig, Masato Hagiwara,
    "Natural Language Processing: Fundamentals and Techniques,"
    Shoeisha. 2016
  • Satoshi Nakamura,
    “多言語音声翻訳技術の最前線,”
    日本発多言語国際情報発信の現状と課題　〜ヒューマンリソースとグローバルコミュニケーションのゆくえ〜, pp233-250, 2016.3.
• Book Chapter
  
  
  
  • Graham Neubig,
    "Multilingual Speech Translation,"
    Acoustic Keyword Book. Korona-sha. 2016. 2016
  • Graham Neubig,
    "Machine Translation: Present and Future,"
    Iwanami Data Science Vol. 2. Iwanami Shoten. 2016
TOP