研究
論文リスト (2016年度:2016年4月-2017年3月)
-
学術論文[査読あり]
-
Quoc Truong Do, Tomoki Toda, Graham Neubig, Sakriani Sakti and Satoshi Nakamura.
"Preserving Word-level Emphasis in Speech-to-speech Translation."
Transactions on Audio, Speech and Language Processing, vol.25, no.3, Dec. 2016.
(第11回 IEEE Signal Processing Society (SPS) Japan Student Journal Paper Award) -
Yuji Oshima, Shinnosuke Takamichi, Tomoki Toda, Graham Neubig, Sakriani Sakti and Satoshi Nakamura.
"Non-Native Text-to-Speech Preserving Speaker Individuality Based on Partial Correction of Prosodic and Phonetic Characteristics."
IEICE Transactions of Information and Systems, vol.E99-D, no.12, pp3132-3139, Dec. 2016. -
三浦明波, Graham Neubig, Sakriani Sakti, 戸田智基, 中村哲.
"中間言語情報を記憶するピボット翻訳手法."
自然言語処理, vol.23, no.5, pp499-528, 2016.12. -
杉山享志朗, 水上雅博, Graham Neubig, 吉野幸一郎, 鈴木優, 中村哲.
"言語横断質問応答に適した機械翻訳評価尺度の調査."
自然言語処理, vol.23, no.5, pp437-461, 2016.12. -
Takuya Hiraoka, Graham Neubig, Sakriani Sakti, Tomoki Toda and Satoshi Nakamura.
"Learning cooperative persuasive dialogue policies using framing."
Speech Communication, vol.84, pp83-96, Nov. 2016. -
Kazuhiro Kobayashi, Tomoki Toda, Tomoyasu Nakano, Masataka Goto, Satoshi Nakamura.
"Improvements of Voice Timbre Control Based on Perceived Age in Singing Voice Conversion."
IEICE Transactions of Information and Systems, vol.E99-D, no.11, pp2767-2777, Nov. 2016. -
Lasguido NIO, Sakriani Sakti, Graham Neubig, Koichiro Yoshino and Satoshi Nakamura.
"Neural Network Approaches to Dialog Response Retrieval and Generation."
IEICE Transactions of Information and Systems, vol.E99-D, no.10, pp2508-2517, Oct. 2016. -
Takuya Hiraoka, Kallirroi Georgila, Elnaz Nouri, David Traum, Satoshi Nakamura.
"Reinforcement Learning of Multi-Party Trading Dialog Policies."
人工知能学会論文誌, vol.31(2016), no.4, pp1-14, Oct. 2016. -
森下 睦, 赤部 晃一, 波多腰 優斗, Graham Neubig, 吉野 幸一郎, 中村 哲.
"統語ベース翻訳のための構文解析器の自己学習."
自然言語処理, vol.23, no.4, pp353-376, Sep. 2016. -
Hiroki Tanaka, Sakriani Sakti, Graham Neubig, Tomoki Toda, Hideki Negoro, Hidemi Iwasaka and Satoshi Nakamura.
"Teaching Social Communication Skills through Human-Agent Interaction."
ACM Transactions on Interactive Intelligent Systems, vol.6, no.2, pp18.1-18.26, Aug. 2016. -
Shinnosuke Takamichi, Tomoki Toda, Alan W. Black, Graham Neubig, Sakriani Sakti, Satoshi Nakamura.
"Postfilters to Modify the Modulation Spectrum for Statistical Parametric Speech Synthesis."
IEEE/ACM Transactions on Audio, Speech, and Language ProcessingVol.24, No.4, pp.755-767, April 2016. -
Shinsuke Mori, Graham Neubig.
"A Comparative Study of Dictionaries and Corpora as Methods for Language Resource Addition."
Language Resources and Evaluation. 50-2, pp. 245-261. 2016. -
Hayato Maki, Tomoki Toda, Sakriani Sakti, Graham Neubig, Satoshi Nakamura.
"Enhancing Event-Related Potentials Based on Maximum a Posteriori Estimation with a Spatial Correlation Prior."
IEICE Transactions on Information and Systems, E99-D-6, pp.1437-1446, 2016.
-
Quoc Truong Do, Tomoki Toda, Graham Neubig, Sakriani Sakti and Satoshi Nakamura.
-
国際会議[査読あり]
- Michael Heck, Sakriani Sakti, Satoshi Nakamura. "ITERATIVE TRAINING OF A DPGMM-HMM ACOUSTIC UNIT RECOGNIZER IN A ZERO RESOURCE SCENARIO." Proc. IEEE SLT, pp . 57-63, Dec 2016.
- Kazuhiro Kobayashi, Tomoki Toda, Satoshi Nakamura. "F0 TRANSFORMATION TECHNIQUES FOR STATISTICAL VOICE CONVERSION WITH DIRECT WAVEFORM MODIFICATION WITH SPECTRAL DIFFERENTIAL." Proc. IEEE SLT, pp . 693-700, Dec 2016.
- Seokhwan Kim, Luis Fernando D’Haro, Rafael E. Banchs, Jason D. Williams, Matthew Henderson, Koichiro Yoshino. "THE FIFTH DIALOG STATE TRACKING CHALLENGE." Proc. IEEE SLT, pp . 511-517, Dec 2016.
- Sakriani Sakti, Seiji Kawanishi, Graham Neubig, Koichiro Yoshino, Satoshi Nakamura. "DEEP BOTTLENECK FEATURES AND SOUND-DEPENDENT I-VECTORS FOR SIMULTANEOUS RECOGNITION OF SPEECH AND ENVIRONMENTAL SOUNDS." Proc. IEEE SLT, pp . 35-42, Dec 2016.
- Wakana Maeda, Yu Suzuki, Satoshi Nakamura. "Fast Text Anonymization using k-anonymity." International Conference on Information Integration and Web-based Applications & Services, Nov. 2016.
- Oliver Adams, Graham Neubig, Trevor Cohn, Steven Bird, Quoc Truong Do and Satoshi Nakamura. "Learning a Lexicon and Translation Model from Phoneme Lattices." In EMNLP, November 2016. (Best Short Paper Award)
- Philip Arthur, Graham Neubig, Satoshi Nakamura. "Incorporating Discrete Translation Lexicons into Neural Machine Translation." In EMNLP, November 2016.
- Rui Hiraoka, Hiroki Tanaka, Sakti Sakriani, Graham Neubig, Satoshi Nakamura. "Personalized Unknown Word Detection in Non-native Language Reading using Eye Gaze." ACM International Conference on Multimodal Interaction (ICMI), pp.66-70, Nov. 2016.
- Hiroki Tanaka, Hiroyoshi Adachi, Norimichi Ukita, Takashi Kudo, Satoshi Nakamura. "Automatic Detection of Very Early Stage of Dementia through Multimodal Interaction with Computer Avatars." ACM International Conference on Multimodal Interaction (ICMI), pp.261-265, Nov. 2016.
- Hiroki Tanaka, Koichiro Yoshino, Makoto Kondo, Kyoshiro Sugiyama and Satoshi Nakamura. "Multimodal Interaction Data between Clinical Psychologists and Students for Attentive Listening Modeling." Oriental Cocosda, pp. 95-98, Oct. 2016.
- Koichiro Yoshino, Satoshi Nakamura. "Data Driven Spoken Dialog Systems for Elderly Care." The 7th symposium on International Collaborative Laboratories(ウルム大学/NAISTワークショップ), Sep. 2016.
- Patrick Lumban Tobing, Tomoki Toda, Hirokazu Kameoka, Satoshi Nakamura. "Acoustic-to-Articulatory Inversion Mapping Based on Latent Trajectory Gaussian Mixture Model." InterSpeech, pp. 953 - 957, Sep. 2016.
- Gábor Pintér, Hiroki Watanabe. "Do GMM Phoneme Classifiers Perceive Synthetic Sibilants as Humans Do?" InterSpeech, pp. 1363 - 1367, Sep. 2016.
- Kazuhiro Kobayashi, Shinnosuke Takamichi, Satoshi Nakamura, Tomoki Toda. "The NU-NAIST Voice Conversion System for the Voice Conversion Challenge2016." InterSpeech, pp. 1667 - 1671, Sep. 2016.
- Satoshi Tsujioka, Sakriani Sakti, Koichiro Yoshino, Graham Neubig, Satoshi Nakamura. "Unsupervised Joint Estimation of Grapheme-to-Phoneme Conversion Systems and Acoustic Model Adaptation for Non-Native Speech Recognition." InterSpeech, pp. 3091 - 3095, Sep. 2016.
- Michael Heck, Sakriani Sakti, Satoshi Nakamura "Supervised Learning of Acoustic Models in a Zero Resource Setting to Improve DPGMM Clustering." InterSpeech, pp. 1310 - 1314, Sep. 2016.
- Quoc Truong Do, Sakriani Sakti, Graham Neubig, Satoshi Nakamura. "Transferring Emphasis in Speech Translation Using Hard-Attentional Neural Network Models." InterSpeech, pp. 2533 - 2537, Sep. 2016.
- Quoc Truong Do, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura "A Hybrid System for Continuous Word-Level Emphasis Modeling Based on HMM State Clustering and Adaptive Training." InterSpeech, pp. 3196 - 3200, Sep. 2016.
- Juliana Miehle, Koichiro Yoshino, Louisa Pragst, Stefan Ultes, Satoshi Nakamura and Wolfgang Minker. "Cultural Communication Idiosyncrasies in Human-Computer Interaction" Proc. SIGDIAL, pp. 74–79. Los Angeles, California, Sep. 2016.
- Masahiro Mizukami, Koichiro Yoshino, Graham Neubig, David Traum, Satoshi Nakamura. "Analyzing the Effect of Entrainment on Dialogue Acts" Proc. SIGDIAL, pp. 310–318. Los Angeles, California, Sep. 2016.
- K. Tanaka, T. Toda, G. Neubig, S. Nakamura. "Real-time vibration control of an electrolarynx based on statistical F0 contour prediction." Proc. EUSIPCO, pp. 1333–1337, Budapest, Hungary, Aug. 2016.
- Yu Suzuki, Satoshi Nakamura. "Assessing the Quality of Wikipedia Editors through Crowdsourcing." Proceedings of Wiki Workshop 2016 in conjunction with WWW 2016, pp1001-1006, April 2016.
-
Michael Heck, Sakriani Sakti, Satoshi Nakamura.
Unsupervised Linear Discriminant Analysis for Supporting DPGMM Clustering in the Zero Resource Scenario.
Procedia Computer Science, Volume 81, 2016, Pages 73-79, ISSN 1877-0509. -
Koichiro Yoshino, Naoki Hirayama, Shinsuke Mori, Fumihiko Takahashi, Katsutoshi Itoyama and Hiroshi G. Okuno.
Parallel Speech Corpora of Japanese Dialects.
Proceedings of The Tenth International Conference on Language Resources and Evaluation (LREC 2016), pp4652-4657, May 2016. - Nurul Lubis, Randy Gomez, Sakriani Sakti, Keisuke Nakamura, Koichiro Yoshino, Satoshi Nakamura and Kazuhiro Nakadai. "Construction of Japanese Audio-Visual Emotion Database and Its Application in Emotion Recognition." Proceedings of The Tenth International Conference on Language Resources and Evaluation (LREC 2016), May 2016.
-
Akiva Miura, Graham Neubig, Michael Paul, Satoshi Nakamura.
"Selecting Syntactic, Non-redundant Segments in Active Learning for Machine Translation."
The 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies (HLT) Long Paper Track. pp. 20-29 June 2016. -
Manaal Faruqui, Yulia Tsvetkov, Graham Neubig, Chris Dyer.
"Morphological Inflection Generation Using Character Sequence to Sequence Learning."
The 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies (HLT) Long Paper Track. pp. 634-643 June 2016. -
Andros Tjandra, Sakriani Sakti, Ruli Manurung, Mirna Adriani and Satoshi Nakamura
”Gated Recurrent Neural Tensor Network”
Proceedings of The 2016 International Joint Conference on Neural Networks (IJCNN 2016), July 2016 -
Hiroki Tanaka, Hiroyoshi Adachi, Norimichi Ukita, Takashi Kudo, Satoshi Nakamura
”Automatic Detection of Very Early Stage of Dementia through Spoken Dialog with Computer Avatars”
International Conference of the IEEE Engineering in Medicine and Biology Society, Aug. 2016. -
Rui Hiraoka, Hiroki Tanaka, Sakti Sakriani, Koichiro Yoshino, Graham Neubig, Satoshi Nakamura
”Eye Gaze-based Unknown Word Detection in Non-native Language Reading using SVMs and Random Forests”
International Conference of the IEEE Engineering in Medicine and Biology Society, Aug. 2016. -
Hiroki Tanaka, Sakriani Sakti, Graham Neubig, Hideki Negoro, Hidemi Iwasaka, Satoshi Nakamura
”Automated Social Skills Training with Audiovisual Information”
International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 2262-2265, Aug. 2016. -
Hayato Maki, Tomoki Toda, Sakriani Sakti, Graham Neubig, and Satoshi Nakamura
”Removing Noise from Event-Related Potentials using a Probabilistic Generative Model with Grouped Covariance Matrices”
International Conference of the IEEE Engineering in Medicine and Biology Society, pp.3728-3731, Aug. 2016.
国際会議[査読なし]
研究会
- 森下 睦, 小田 悠介, Graham Neubig, 吉野 幸一郎, 須藤 克仁, 中村 哲. "ニューラル機械翻訳におけるミニバッチ構成法の違いによる影響の調査." 言語処理学会第23回年次大会(NLP2017). 茨城. 2017年3月.
- 札場 寛之, 小田 悠介, 吉野 幸一郎, Graham Neubig, 中村 哲. "目的言語側の構造を考慮した自然言語からの構文的に正しいソースコード生成." 言語処理学会第23回年次大会(NLP2017). 茨城. 2017年3月.
- 石川 葉子, 水上 雅博, 吉野 幸一郎, Sakriani Sakti, 鈴木 優, 中村 哲. "感情表現を用いた説得対話システム." 言語処理学会第23回年次大会(NLP2017). 茨城. 2017年3月.
- 小田 悠介, Philip Arthur, Graham Neubig, 吉野 幸一郎, 中村 哲. "二値符号予測と誤り訂正に基づくコンパクトなニューラルネットワーク翻訳モデル." 言語処理学会第23回年次大会(NLP2017). 茨城. 2017年3月.
- 水上 雅博, 吉野 幸一郎, Graham Neubig, 中村 哲. "エントレインメント分析に基づく応答文選択モデルの評価." 言語処理学会第23回年次大会(NLP2017). 茨城. 2017年3月.
- 田中 宏昌, 鈴木 優, 山崎 将太朗, 加藤 晃, 吉野 幸一郎, 中村 哲. "アンサンブル学習を用いたmRNA配列からの翻訳効率予測." 研究報告バイオ情報学(BIO), Vol.2017-BIO-49, No.2, pp.1-6, Mar. 2017.
- Faiz Ilham,Sakriani Sakti, Ayu Purwarianti, Satoshi Nakamura. "LSTM-RNN for Incremental Sentence Compression." 音響学会講演論文集, 3-5-8, pp. 85-86, Mar. 2017.
- 高道 慎之介,中村 哲. "GMMに基づく固有声変換のための変調スペクトル制約付きトラジェクトリ学習・適応." 日本音響学会2017年春季研究発表会講演論文集, 1-6-9, Mar. 2017. (独創研究奨励賞 板倉記念 受賞)
"様々な分野における対訳コーパスを用いた構文解析器の自己学習効果の検証."
情報処理学会 第226回自然言語処理研究会(SIG-NL). 東京. 2016年5月.
(学生奨励賞)
"音声対話システムの概観とその機能"
情報処理学会 音学シンポジウム2016(第111回音楽情報科学研究会), 東京都港区, 2016年5月
"木構造を中間表現とするピボット翻訳手法"
情報処理学会研究報告, Vol. 2016-NL-227 No. 5, July. 2016.
"Encoder-Decoderモデルにおける出力長制御."
情報処理学会研究報告, Vol. 2016-NL-227 No. 5, July. 2016.
"アバターとの対話によるマルチモーダル情報を伴った早期認知症の検出."
情報処理学会研究報告,vol.2016-ASD-5, No. 14, Aug. 2016.
大会講演
- K. Tanaka, T. Toda, S. Nakamura. "Evaluation of electrolarynx controlled by real-time statistical F0 prediction." 5th Joint Meeting of the ASA and the ASJ, 1aSC25, Hawaii, USA, Nov. 2016.
- K. Kobayashi, T. Toda, S. Nakamura. "Low delay statistical singing voice conversion with direct waveform modification based on spectral differential considering global variance." 5th Joint Meeting of the ASA and the ASJ, 1aSC16, Hawaii, USA, Nov. 2016.
- 前田若菜, 鈴木優, 吉野幸一郎, 中村 哲. "文脈からの推定を考慮した非構造化テキストデータの匿名化手法." 情報科学技術フォーラム講演論文集.
- 水上 雅博, David Traum, 吉野 幸一郎, Graham Neubig, 中村 哲. "ユーザ属性に基づく対話行為と語彙選択のエントレインメント分析." 人工知能学会全国大会, 2O5-OS-23b-4, Jun. 2016.
- 品川 政太朗, 吉野 幸一郎, ニュービッグ グラム, 中村 哲. "キャプションからの画像生成を行うニューラルネットへの対話的修正の導入と検討." 人工知能学会全国大会, 1A4-OS-27b-4, Jun. 2016.
- 杉山 享志朗, 吉野 幸一郎, 田中 宏季, 近藤 真人, ニュービッグ グラム, 中村 哲. "傾聴対話コーパスの作成と知識獲得行為の分析." 人工知能学会全国大会, 4K4-5, Jun. 2016.
招待講演
- Satoshi Nakamura. "Toward Simultaneous, Natural and Multimodal Speech-to-speech Translation." Microsoft Research Asia Faculty Summit 2016, Seoul, Nov. 2016.
- 中村 哲. "言語の壁を超える音声言語コミュニケーション研究の現状と今後." 第27回学士会 関西茶話会, 2017年2月18日.
- 中村 哲. "音声研究と自然言語研究の融合に向けて-音声翻訳研究の過去と未来-." 信学技報, Vol. 116, No. 378, pp. 121-122, Dec. 2016.
- 中村 哲. "ビッグデータとIoTの活用でなにができるか?-知識・言語・コミュニケーション技術を中心に-." スマートインフラ研究会, 2016年10月.
- 鈴木 優. "NAISTにおけるビッグデータ解析の取り組み." 第15回情報科学技術フォーラム(FIT2016), Sep. 2016.
- Satoshi Nakamura. "Bridging different Languages, Countries, and Cultures by Speech to Speech Translation Research." Talk at University of Ulm, August 2016.
- Satoshi Nakamura. "Bridging different Languages, Countries, and Cultures by Speech to Speech Translation Research." InterACT25, July 2016.
- 中村 哲. "都市をスマート化する知能コミュニケーション技術." スマートシティエキスポ 2016, 2016年6月.
- Graham Neubig "自然言語とプログラムの間の自動翻訳" 情報処理学会 連続セミナー2016, 2016年6月.
解説記事、コラム
図書