Research

Publication List: Paper (Fiscal Year 2012: April/2012-March/2013)

• Scientific Journals [Peer Reviewed]
  
  
  
  • Tomoaki Nakamura, Komei Sugiura, Takayuki Nagai, Naoto Iwahashi, Tomoki Toda, Hiroyuki Okada, Takayuki Omori.
    "Learning novel objects for extended mobile manipulation."
    Journal of Intelligent and Robotic Systems, Vol. 66, No. 1-2, pp. 187-204, Apr. 2012.
  • Graham Neubig, Taro Watanabe, Eiichiro Sumita, Shinsuke Mori, Tatsuya Kawahara.
    "Joint Phrase Alignment and Extraction for Statistical Machine Translation"
    Journal of Information Processing, 20-2, pp.512-523. April 2012.
  • Sakriani Sakti, Michael Paul, Andrew Finch, Xinhui Hu, Jinfu Ni, Noriyuki Kimura, Shigeki Matsuda, Chiori Hori, Yutaka Ashikari, Hisashi Kawai, Hideki Kashioka, Eiichiro Sumita, Satoshi Nakamura
    "Distributed Speech Translation Technologies for Multiparty Multilingual Communication"
    ACM Trans. Speech Lang. Process., vol. 9, Issue 2, Article 4, July 2012, DOI = 10.1145/2287710.2287712.
  • Hansjorg Hofmann, Sakriani Sakti, Chiori Hori, Hideki Kashioka, Satoshi Nakamura, Wolfgang, Minker.
    "Sequence-based Pronunciation Variation Modeling for Spontaneous ASR using a Noisy Channel Approach"
    IEICE Trans. Inf. & Syst., vol. E95-D, pp. 2084-2093, August 2012
  • Tomoki Toda, Mikihiro Nakagiri, Kiyohiro Shikano.
    "Statistical voice conversion techniques for body-conducted unvoiced speech enhancement."
    IEEE Transactions on Audio, Speech and Language Processing, Vol. 20, No. 9, pp. 2505-2517, Sep. 2012.
  • Daniel Flannery, Yusuke Miyao, Graham Neubig, Shinsuke Mori.
    "A Pointwise Approach to Training Dependency Parsers from Partially Annotated Corpora"
    Journal of Natural Language Processing, 19-3, pp.167-192. September 2012.
• International Conference [Peer Reviewed]
  
  
  
  • Tomoki Toda.
    "Statistical approaches to enhancement of body-conducted speech detected with non-audible murmur microphone."
    Proc. of ICME CME, pp. 623-628, Hyogo, Japan, July 2012.
  • Graham Neubig, Taro Watanabe, Shinsuke Mori, Tatsuya Kawahara.
    "Machine Translation without Words through Substring Alignment"
    The 50th Annual Meeting of the Association for Computational Linguistics (ACL), pp.165-174. July 2012.
  • Graham Neubig, Taro Watanabe, Shinsuke Mori.
    "Inducing a Discriminative Parser to Optimize Machine Translation Reordering"
    Conference on Empirical Methods in Natural Language Processing and Natural Language Learning (EMNLP-CoNLL), pp.843-853. July 2012.
  • Tomoki Toda, Takashi Muramatsu, Hideki Banno.
    "Implementation of computationally efficient real-time voice conversion."
    Proc. of INTERSPEECH, Portland, USA, Sep. 2012.
  • Shinnosuke Takamichi, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai, Sakriani Sakti, Satoshi Nakamura.
    "An evaluation of parameter generation methods with rich context models in HMM-based speech synthesis."
    Proc. of INTERSPEECH, Portland, USA, Sep. 2012.
  • Mayumi Kishimoto, Tomoki Toda, Hironori Doi, Sakriani Sakti, Satoshi Nakamura.
    "Model training using parallel data with mismatched pause positions in statistical esophageal speech enhancement."
    Proc. ICSP, pp. 590-594, Beijing, China, Oct. 2012.
  • Lasguido, Sakriani Sakti, Graham Neubig, Tomoki Toda, Mirna Adriani, Satoshi Nakamura.
    "Developing Non-Goal Dialog System based on Examples of Drama Television."
    Proc. of the 4th International Workshop on Spoken Dialog Systems (IWSDS 2012), pp. 315-320, Ermenonville, France, Nov. 2012.
  • Hiroki Tanaka, Sakriani Sakti, Graham Neubig, Tomoki Toda, Nick Campbell and Satoshi Nakamura. "Non-verbal Cognitive Skills and Autistic Conditions: An Analysis and Training Tool."
    in Proc. 3rd IEEE CogInfoCom 2012, pp. 41-46, Kosice, Slovakia, Dec. 2012.
  • Hironori Doi, Tomoki Toda, Tomoyasu Nakano, Masataka Goto, and Satoshi Nakamura.
    "Singing Voice Conversion Method Based on Many-to-Many Eigenvoice Conversion and Training Data Generation Using A Singing-to-Singing Synthesis System."
    APSIPA ASC 2012, Dec. 2012.
  • Graham Neubig, Kevin Duh, Masaya Ogushi, Takatomo Kano, Tetsuo Kiso, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "The NAIST MachineTranslation System for IWSLT2012."
    IWSLT 2012, pp54-60, HongKong, China, Dec. 2012 [THE BEST PAPER AWARD (Short Paper in Regular Session Category)]
  • Michael Heck, Keigo Kubo, Matthias Sperber, Sakriani Sakti, Sebastian Stuker, Christian Saam, Kelvin Kilgour, Christian Mohr, Graham Neubig, Tomoki Toda, Satoshi Nakamura, Alexander Waibel
    "The KIT-NAIST (Contrastive) English ASR System for IWSLT 2012."
    IWSLT 2012, pp91-95, HongKong, China, Dec. 2012
  • Takatomo Kano, Sakriani Sakti, Shinnosuke Takamichi, Graham Neubig, Tomoki Toda, Satoshi Nakamura.
    "A Method for Translation of Paralinguistic Information."
    IWSLT 2012, pp158-163, HongKong, China, Dec. 2012.
  • Hiroaki Shimizu, Masao Utiyama, Eiichiro Sumita, Satoshi Nakamura.
    "Minimum Bayes-Risk Decoding Extended with Two Methods: NAIST-NICT at IWSLT 2012."
    IWSLT 2012, pp117-120, HongKong, China, Dec. 2012.
  • Christian Saam, Christian Mohr, Kelvin Kilgour, Michael Heck, Matthias Sperber, Keigo Kubo, Sebastian Stuker, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura, Alexander Waibel
    "The 2012 KIT and KIT-NAIST English ASR Systems for the IWSLT Evaluation."
    IWSLT 2012, pp87-90, HongKong, China, Dec. 2012.
  • Auliya Sani, Sakriani Sakti, Graham Neubig, Tomoki Toda, Adi Mulyanto, Satoshi Nakamura.
    "TOWARDS LANGUAGE PRESERVATION: PRELIMINARY COLLECTION AND VOWEL ANALYSIS OF INDONESIAN ETHNIC SPEECH DATA."
    Proc. of Oriental COCOSDA 2012, Macau China, pp. 118-122, Macau, China, Dec. 2012. [BEST STUDENT PAPER AWARD]
  • Miyuki Itoi, Ryoichi Miyazaki, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano.
    "Blind speech extraction for non-audible murmur speech with speaker's movement noise."
    Proc. ISSPIT, Ho Chi Minh City, Vietnam, Dec. 2012.
  • Graham Neubig, Kevin Duh.
    "How Much is Said in a Tweet? A Multilingual, Information-theoretic Perspective"
    AAAI Spring Symposium on Analyzing Microtext. March 2013.
• International Conference ［Without Peer Review］
  
  
  
  • T. Toda.
    General concepts and framework of HMM-based speech synthesis.
    Tutorial on HMM-based statistical speech synthesis in Workshop at Shanghai Jiao Tong University, Shanghai, China, Oct. 2012 (Tutorial).
  • Y. Odagaki, S. Sakti, G. Neubig, T. Toda, S. Nakamura.
    An ERP Analysis of the World-Sense and Semantics Mismatches in Japanese Sentences.
    The Australasian Cognitive Neuroscience Conference (ACNS-2012), Brisbane, Australia, Nov. 2012.
  • T. Toda.
    Statistical voice conversion and its real-time applications.
    Workshop on Frontiers in Speech and Language Technologies and Their Applications, Hefei, China, Dec. 2012 (invited lecture).
  • T. Toda.
    Statistical approach to voice conversion and its applications for augmented human communication.
    The 8th International Symposium on Chinese Spoken Language Processing (ISCSLP-2012), Hong Kong, China, Dec. 2012 (Tutorial).
  • T. Toda.
    Voice conversion.
    Winter School on Speech and Audio Processing (WiSSAP 2013), Chennai, India, Feb. 2013 (invited lecture).
• Research Report
  
  
  
  • [In JAPANESE] Miyuki Itoi, Ryouichi Miyazaki, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano
    "Blind speech extraction for non-audible murmur speech with speaker's movement noise."
    Technical Research Report of IEICE, Vol. 112, No. 76, EA2012-40, pp. 43-48, June 2012.
  • [In JAPANESE] Tetsuo Sasada, Shinsuke Mori, Graham Neubig, Tatsuya Kawahara.
    "Training a Word Segmenter from a Feature Frequency File and Partially Annotated Corpora"
    IPSJ-SIG The 207th Annual Meeting of Natural Learning Processing (NL-207). Hokkaido. July, 2012.
    
  • [In JAPANESE] Shinnosuke Takamichi, Tomoki Toda, Yoshinori Shiga, Yasushi Kawai, Sakriani Sakti, Graham Neubig, Satoshi Nakamura
    "A Study on HMM-Based Speech Synthesis Using Rich Context Models"
    Research Report of IPSJ, Vol. 2012-SLP-92, No. 10, pp. 1-6, July 2012.
  • [In JAPANESE] Hironori Doi, Tomoki Toda, Tomoyasu Nakano, Masataka Goto, Satoshi Nakamura.
    「VocaListenerによる学習データ生成を利用した多対多固有声変換に基く歌声声質変換」
    Research Report of IPSJ, Vol. 2012-MUS-96, No. 5, pp. 1-9, Aug. 2012. [BEST PRESENTATION AWARD (WITH THE MOST VOTE)]
  • [in Japanese] Takuto Moriguchi, Tomoki Toda, Motoaki Sano, Hiroshi Sato, Graham Neubig, Sakriani Sakti, Satoshi Nakamura.
    "Implementation of real-time statistical voice conversion on a DSP"
    Technical Report of IEICE, SP2012-73, pp. 7-12, Nov. 2012.
  • [in Japanese] Tatsuo Inukai, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura.
    "Spectral parameter variation between utterances of the same sentence by a single speaker and its prediction"
    Technical Report of IEICE, SP2012-74, pp.13-18, Nov. 2012.
  • [in Japanese] Shinnosuke Takamichi, Tomoki Toda, Yoshinori Shiga, Sakriani Sakti, Graham Neubig, Satoshi Nakamura.
    "Improvements of HMM-based speech synthesis using rich context models"
    Technical Report of IEICE, SP2012-78, pp.37-42, Nov. 2012.
  • [in Japanese] Hiroki Tanaka, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura.
    「非言語認知スキルからの自閉症スペクトラム指数の自動測定」
    Research Report of JSISE, vol. 27, no. 4, pp. 44-46, Nov. 2012.
  • [in Japanese]Tomoki Fujita, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "Towards a Speech Translation System Considering Simultaneity"
    Research Report of JSISE, Vol. 2012-NL-209, No. 13, pp. 1-5, Nov. 2012.
    
  • [in Japanese]Yuki Yamauchi, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "Answer Sentence Generation for Guiding Users to New Topics with Relationships between Words in Spoken Dialog Systems"
    IPSJ SIG Technical Report, Vol. 2012-SLP-94, No. 3, pp. 1-7, Dec. 2012.
  • [in Japanese]Takuya Hiraoka, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "Dialog management based on guiding users to new topics in persuasive dialogue systems"
    IPSJ SIG Technical Report, Vol. 2012-SLP-94, No. 4, pp. 1-6, Dec. 2012.
  • [in Japanese]Shinnosuke Takamichi, Tomoki Toda, Yoshinori Shiga, Sakriani Sakti, Graham Neubig, Satoshi Nakamura.
    "F0 Contour Generation Using Rich Context Models in HMM-Based Speech Synthesis"
    Technical Report of IEICE, SP2012-104, pp. 37-42, Jan. 2013.
  • [in Japanese]Miyuki Itoi, Ryoichi Miyazaki, Tomoki Toda, Saruwatari Hiroshi, Kiyohiro Shikano.
    "Blind speech extraction based on multichannel diverse sensing for non-audible murmur speech with speaker's movement noise"
    Technical Report of IEICE, Vol. 112, No. 388, EA2012-119, pp. 1-6, Jan. 2013.
  • [in Japanese]Hiroki Tanaka, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura.
    "Measurement of Autistic Traits using Non-verbal Communication Skills"
    Technical Report of IEICE, IMQ2012-34-IMQ2012-91, pp. 223-226, Mar. 2013.
• Conference Presentation
  
  
  
  • [In JAPANESE] Yuki Yamauchi, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "Answer Sentence Generation using Relationships between Words for Guiding Users to New Topics in Spoken Dialog Systems"
    Proceeding of ASJ, 2-1-11, pp. 81-82, Sep. 2012.
  • [In JAPANESE] Takuya Hiraoka, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura
    "A study on dialog management in persuasive dialog systems"
    Proceeding of ASJ, 2-1-12, pp. 83-84, Sep. 2012.
  • [In JAPANESE] Takamoto Kano, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura.
    "A duration-sensitive speech translation system"
    Proceeding of ASJ, 3-P-23, pp. 181-182, Sep. 2012.
  • [In JAPANESE] Takuto Moriguchi, Tomoki Toda, Motoaki Sano, Hiroshi Sato, Graham Neubig, Sakriani Sakti, Satoshi Nakamura
    "Implementation of real-time body-conducted voice conversion on DSP"
    Proceeding of ASJ, 1-2-2, pp. 217-218, Sep. 2012.
  • [In JAPANESE] Hironori Doi, Tomoki Toda, Tomoyasu Nakano, Masataka Goto, Satoshi Nakamura
    "Singing voice conversion based on many-to-many eigenvoice conversion and training data generation with singing synthesis"
    Proceeding of ASJ, 1-2-7, pp. 231-232, Sep. 2012.
  • [In JAPANESE] Shinnosuke Takamichi, Tomoki Toda, Yoshinori Shiga, Sakriani Sakti, Graham Neubig, Satoshi Nakamura
    "A Study on a Selection Method of Rich Context Models in HMM-based Speech Synthesis"
    Proceeding of ASJ, 2-2-1 pp. 273-274, Sep. 2012.
  • [In JAPANESE] Tatsuo Inukai, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura
    "Spectral parameter variation between utterances of the same sentence by a single speaker and its prediction"
    Proceeding of ASJ, 2-2-8, pp. 291-292, Sep. 2012.
  • [In JAPANESE] Miyuki Itoi, Ryoichi Miyazaki, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano.
    "Blind speech extraction for non-audible murmur speech recorded by various microphones"
    Proceeding of ASJ, 3-9-10, pp. 695-698, Sep. 2012.
  • Yu Odagaki, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura
    "An ERP Analysis of the World-Sense and Semantics Mismatches in Japanese Sentences"
    The 35th Annual Meeting of the Japan Neuroscience Society Nagoya, Japan, Sep. 2012
  • [In Japanese]Miyuki Itoi, Ryoichi Miyazaki, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano.
    "ユーザ動作に伴う雑音を含む非可聴つぶやき音声における6チャネルブラインド音声抽出."
    ASJ2012, Dec. 2012.
  • [In Japanese]Masaya Ogushi, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "音声認識と機械翻訳のランク学習による同時最適化"
    The 19th Annual Meeting of The Association for Natural Language Processing，pp.564-567，Mar. 2013
  • [In Japanese]Takuto Moriguchi, Tomoki Toda, Motoaki Sano, Hiroshi Sato, Graham Neubig, Sakriani Sakti, Satoshi Nakamura.
    "\Implementation of real-time alaryngeal-speech-to-speech conversion on DSP"
    Proceedings of ASJ, 1-7-2, pp. 265-266, Mar. 2013.
  • [In Japanese]Shinnosuke Takamichi, Tomoki Toda, Yoshinori Shiga, Sakriani Sakti, Graham Neubig, Satoshi Nakamura.
    "Quality Improvements with Rich Context Models for Spectral and F0 Components in HMM-based Speech Synthesis"
    Proceedings of ASJ, 1-7-10, pp. 287-288, Mar. 2013.
  • [In Japanese]Kou Tanaka, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura.
    "Investigation of converted acoustic features in statistical electrolaryngeal speech conversion"
    Proceedings of ASJ, 2-7-8, pp. 331-332, Mar. 2013.
  • [In Japanese]Kazuhiro Kobayashi, Hironori Doi, Tomoki Toda, Tomoyasu Nakano, Masataka Goto, Graham Neubig, Sakriani Sakti, Satoshi Nakamura.
    "Investigation of Acoustic Features for Voice Conversion to Control Perceptual Age of Singing Voice"
    Proceedings of ASJ, 2-7-14, pp. 347-348, Mar. 2013.
  • [In Japanese]Miyuki Itoi, Ryoichi Miyazaki, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano.
    "Evaluation of blind speech extraction based on multichannel diverse sensing for non-audible murmur speech with speaker's movement noise ユーザ動作雑音を含む非可聴つぶやき音声における多チャネル異種センサ統合に基づくブラインド音声抽出の評価"
    Proceedings of ASJ, 2-10-2, pp. 725-728, Mar. 2013.
  • [In Japanese]Tatsuo Inukai, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura.
    "An evaluation of prediction of intra-speaker spectral parameter variation between utterances of the same sentence"
    Proceedings of ASJ, 3-7-3, pp. 357-358, Mar. 2013.
  • [In Japanese]Yuki Yamauchi, Graham Neubig, Sakti Sakriani, Tomoki Toda, Satoshi Nakamura.
    "An Extension and Evaluation of Answer Sentence Generation using Relationships between Terms for Guiding Users to New Topics in Spoken Dialog Systems"
    Proceedings of ASJ, 3-9-2, pp. 87-88, Mar. 2013.
  • [In Japanese]Takuya Hiraoka, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura.
    "Dialogue corpus analysis for building persuasive dialogue system"
    Proceedings of ASJ, 3-9-3, pp. 89-90, Mar. 2013.
• Commentary Article
  
  
  
  • [In JAPANESE] Tomoki Toda
    「音声合成技術 進化の行方」
    PROJECT DESIGN 月刊「事業構想」2012年11月号, Oct. 2012.
  • 戸田 智基
    「サイレント音声コミュニケーションのための音声強調技術」
    ケミカルエンジニヤリング, Vol. 58, No. 3, pp. 25-30, Mar. 2013.
  TOP