発表文献 (2014/01-2014/12)

2003200420052006200720082009201020112012
2013201420152016201720182019202020212022

国際会議(査読あり)

  • Ryan Price, Kenichi Iso, Koichi Shinoda
  • Speaker Adaptation of Deep Neural Networks Using a Hierarchy of Output Layers
  • Proc. Spoken Language Technology (SLT) Workshop, pp. 153-158, Dec. 7, 2014
  • Yuan Liang, Koji Iwano, Koichi Shinoda
  • An Efficient Error Correction Interface for Speech Recognition on Mobile Touchscreen Devices
  • Proc. Spoken Language Technology (SLT) Workshop, pp. 454-459, Dec. 7, 2014
  • Nakamasa Inoue, Koichi Shinoda
  • n-Gram Models for Video Semantic Indexing
  • Proc. ACM Multimedia (MM), pp. 777-780, Nov. 3, 2014
  • Tommi Kerola, Nakamasa Inoue, Koichi Shinoda
  • Spectral Graph Skeletons for 3D Action Recognition
  • Proc. Asian Conference on Computer Vision (ACCV), pp. 1-16, Nov. 1, 2014
  • Yuan Liang, Koji Iwano, Koichi Shinoda
  • Simple Gesture-based Error Correction Interface for Smartphone Speech Recognition
  • Proc. Interspeech, pp. 1194-1198, Sep. 16, 2014
  • Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
  • Discriminative PLDA training with application-specific loss functions for speaker verification
  • Proc. Odyssey Workshop, pp. 26-32, Jun. 16, 2014
  • Sangeeta Biswas, Johan Rohdin, Koichi Shinoda
  • i-Vector Selection for Effective PLDA Modeling in Speaker Recognition
  • Proc. Odyssey Workshop, pp. 100-105, Jun. 16, 2014
  • Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
  • Constrained Discriminative PLDA Training for Speaker Verification
  • Proc. International Conference on Acoustic Speech and Signal Processing (ICASSP), pp. 1689-1693, May 4, 2014
  • Zhuolin Liang, Nakamasa Inoue, Koichi Shinoda
  • Event Detection by Velocity Pyramid
  • Proc. Multimedia Modeling (MMM), pp. 353-364, Jan. 6, 2014

国際会議(査読なし)

  • Nakamasa Inoue, Zhuolin Liang, Mengxi Lin, Tran Hai Dang, Koichi Shinoda, Zhang Xuefeng, Kazuya Ueki
  • TokyoTech-Waseda at TRECVID 2014
  • Proc. TRECVID workshop, pp. 1-13, Nov. 9, 2014

国内会議(査読なし)

  • Yuan Liang, Koji Iwano, Koichi Shinoda
  • Error Correction Using Long Context Match for Smartphone Speech Recognition
  • Technical Reports of IPSJ SLP, vol. 104, no. 22, pp. 1-6, Dec. 16, 2014
  • Yuan Liang, Koji Iwano, Koichi Shinoda
  • An Efficient Error Correction Method for Smartphone Speech Recognition
  • Proc. ASJ 2014 Autumn Meeting, pp. 29-30, Sep. 5, 2014
  • 押尾 翔平, 岩野 公司, 篠田 浩一
  • 口唇の深度画像を用いたマルチモーダル音声認識
  • 情報処理学会研究報告 SLP, vol. 102, no. 2, pp. 1-6, Jul. 24, 2014
  • Nataliia Biriukova, Kotaro Funakoshi, Koichi Shinoda
  • Collection and analysis of multi-party interaction data for automatic boredom recognition
  • Proc. The 28th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI) 2014, pp. 1-4, May 13, 2014
  • 森 宏太郎, 井上 中順, 篠田 浩一
  • Deep Learningを用いた映像のセマンティックインデクシングのための特徴次元削減
  • 2014年電子情報通信学会総合大会講演論文集, pp. 85, Mar. 18, 2014
  • Zhuolin Liang, Nakamasa Inoue, Koichi Shinoda
  • Velocity Pyramid for Event Detection
  • Technical Reports of IEICE PRMU, vol. 113, no. 493, pp. 13-18, Mar. 13, 2014
  • Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
  • Discriminatively Trained PLDA with Partially Preserved Model Assumptions in Speaker Verification
  • Proc. ASJ 2014 Spring Meeting, pp. 99-100, Mar. 12, 2014
  • Sangeeta Biswas, Johan Rohdin, Koichi Shinoda
  • Training Multiple PLDA Models by Clustered I-Vectors for Speaker Verification
  • Proc. ASJ 2014 Spring Meeting, pp. 97-98, Mar. 12, 2014
  • Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
  • Robust 0-1 Loss Training for PLDA in Speaker Verification
  • Proc. ASJ 2014 Spring Meeting, pp. 101-102, Mar. 12, 2014
  • 井上 中順, 森 宏太郎, Liang Zhuolin, 篠田 浩一
  • TRECVID 映像意味インデクシングのための音声・音響技術
  • 日本音響学会2014年春季研究発表会講演論文集, pp. 129-130, Mar. 11, 2014
  • 井上 中順, 篠田 浩一
  • 高速な画像分類のためのNeighbor-to-Neighbor探索
  • 電子情報通信学会技術研究報告 PRMU, vol. 113, no. 493, pp. 97-102, Mar. 6, 2014
  • 河原達也, 篠田 浩一, 堀貴明, 堀智織, 篠崎隆宏
  • 「音声認識」は今後こうなる!
  • SIG-SLP第100回記念シンポジウム, page 6, Jan. 31, 2014

基調講演

  • 篠田 浩一
  • 映像意味検索の未来
  • 第17回画像の認識・理解シンポジウム (MIRU), Jul. 29, 2014

招待講演・チュートリアル

  • 篠田 浩一
  • Deep Learningによる新しい音声認識パラダイム
  • 日本神経回路学会主催セミナー「Deep Learningが拓く世界」, Aug. 26, 2014
  • 井上 中順, 篠田 浩一
  • Neighbor-To-Neighbor Search for Fast Coding of Feature Vectors
  • 第17回画像の認識・理解シンポジウム (MIRU), Jul. 29, 2014
  • 篠田 浩一
  • 映像意味検索技術の最新動向
  • NEC Laboratories, Jul. 4, 2014
  • Koichi Shinoda
  • Robust Video Information Retrieval using Speech Technologies
  • Language Technologies Institute, Carnegie Mellon University, Jun. 20, 2014
  • 篠田 浩一
  • 映像検索への音声工学からのアプローチ
  • 音学シンポジウム2014, May 24, 2014
  • 篠田 浩一
  • 映像意味検索技術の最新動向
  • 日本音響学会2014年春季研究発表会講演論文集, pp. 531-532, Mar. 10, 2014
  • 篠田 浩一
  • 映像意味検索の現状と課題
  • 電子情報通信学会技術研究報告 EMM, vol. 113, no. 480, pp. 1-2, Feb. 28, 2014
  • Koichi Shinoda
  • Video Semantic Indexing Using Speech Technologies
  • Dublin City University, Jan. 6, 2014

選抜講演

  • Florian Metze, Koichi Shinoda
  • Semantics for Large-Scale Multimedia: New Challenges for NLP
  • ACL2014, Jun. 22, 2014