"Zehua Zhou,Haoyuan Yang,Takahiro Shinozaki","Self-Supervised Speaker Verification With Adaptive Threshold and Hierarchical Training","ICASSP 2024",,,,,"pp. 12141-12145",2024,Apr.
"YANG Haoyuan,OKAMOTO Takuma,SHINOZAKI Takahiro","Investigating Deep Prompting Approach in Spoken Language Acquisition Agent","日本音響学会2023年秋季研究発表会","日本音響学会2023年秋季研究発表会講演論文集",,,,"  3-Q-20",2023,Sept.
"ZHU Tingyuan,OKAMOTO Takuma,SHINOZAKI Takahiro","A preliminary investigation of Poisson flow model for singing voice synthesis","日本音響学会2023年秋季研究発表会","日本音響学会2023年秋季研究発表会講演論文集",,,,"  2-Q-41",2023,Sept.
"Takahiro Shinozaki,楊 鎬源,Phurich Saengthong,Kota Kawakita,岡本 拓磨","音声言語獲得を行う自律エージェントの構成法 の考察とシステム実装","第41回 日本ロボット学会学術講演会",,,,,,2023,Sept.
"Yu Iwamoto,Takahiro Shinozaki","Memory Network-Based End-To-End Neural ES-KMeans for Improved Word Segmentation","INTERSPEECH 2023",,,,,"pp. 486-490",2023,Aug.
"Ryota Komatsu,Yusuke Kimura,Takuma Okamoto,Takahiro Shinozaki","Continuous Action Space-based Spoken Language Acquisition Agent Using Residual Sentence Embedding and Transformer Decoder","ICASSP",,,,,,2023,June
"Yidong Wang,Hao Chen,Qiang Heng,Wenxin Hou,Yue Fan,Zhen Wu,Jindong Wang,Marios Savvides,Takahiro Shinozaki,Bhiksha Raj,Bernt Schiele,Xing Xie","FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning","The Eleventh International Conference on Learning Representations",,,,,,2023,May
"Ryota Komatsu,Yusuke Kimura,岡本 拓磨,Takahiro Shinozaki","残差文埋め込みを用いた連続行動空間に基づく音声言語獲得エージェント","日本音響学会2023年春季研究発表会","日本音響学会2023年春季研究発表会講演論文集",,,,"  2-3Q-1",2023,Mar.
"Takafumi Moriya,Hiroshi Sato,Tsubasa Ochiai,Marc Delcroix,Takahiro Shinozaki","Streaming End-to-End Target-Speaker Automatic Speech Recognition and Activity Detection",,"IEEE Access",,"vol. 11",,"pp. 13906-13917",2023,Feb.
"Yidong Wang,Bowen Zhang,Wenxin Hou,Zhen Wu,Jindong Wang,Takahiro Shinozaki","Margin Calibration for Long-Tailed Visual Recognition","Asian Conference on Machine Learning 2022 (ACML2022)",,,,,,2022,Dec.
"Mingxin Zhang,Takahiro Shinozaki","DNN-Rule Hybrid Dyna-Q for Sample-Efficient Task-Oriented Dialog Policy Learning","APSIPA2022",,,,,"pp. 1431-1437",2022,Nov.
"Yidong Wang,Hao Chen,Yue Fan,Wang Sun,Ran Tao,Wenxin Hou,Renjie Wang,Linyi Yang,Zhi Zhou,Lan-Zhe Guo,Heli Qi,Zhen Wu,Yu-Feng Li,Satoshi Nakamura,Wei Ye,Marios Savvides,Bhiksha Raj,Takahiro Shinozaki,Bernt Schiele,Jindong Wang,Xing Xie,Yue Zhang","USB: A Unified Semi-supervised Learning Benchmark for Classification","NeurIPS 2022",,,,,,2022,Nov.
"Ao Liu,Zhen Wu,Jindong Wang,Wenxin Hou,Yidong Wang,Hao Wu,Takahiro Shinozaki,Manabu Okumura,Yue Zhang","Unlabeled Data for Target-Oriented Opinion Words Extraction,","The 29th International Conference on Computational Linguistics (COLING 2022)",,,,,,2022,Oct.
"Yidong Wang,Hao Wu,Ao Liu,Wenxin Hou,Zhen Wu,Jindong Wang,Takahiro Shinozaki,Manabu Okumura,Yue Zhang","Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction","COLING2022",,,,,"pp. 7075?7085",2022,Oct.
"Ryota Komatsu,岡本 拓磨,Takahiro Shinozaki","実音声を用いた音声言語獲得エージェントの評価","日本音響学会2022年秋季研究発表会","日本音響学会2022年秋季研究発表会講演論文集",,,,"  3-Q-11",2022,Sept.
"Meikin Cyou,Takahiro Shinozaki","高効率対話方策学習のための規則知識を統合した深層DYNA-Q","日本音響学会2022年秋季研究発表会","日本音響学会2022年秋季研究発表会講演論文集",,,,"  3-8-8",2022,Sept.
"Takafumi Moriya,芦原 孝典,安藤 厚志,佐藤 宏,田中 智大,松浦 孝平,増村 亮,デルクロア マーク,Takahiro Shinozaki","Hybrid RNN-T/Attention 音声認識モデルにおける Triggered Chunkwise Attention と内部言語モデル統合の検討","日本音響学会2022年秋季研究発表会","日本音響学会2022年秋季研究発表会講演論文集",,,,"  2-Q-24",2022,Sept.
"Longfei Yang,Jinsong Zhang,Takahiro Shinozaki","Self-Supervised Learning with Multi-Target Contrastive Coding for Non-Native Acoustic Modeling of Mispronunciation Verification","INTERSPEECH 2022",,,,,"pp. 4312-4316",2022,Sept.
"Longfei Yang,Wenqing Wei,Sheng Li,Jiyi Li,Takahiro Shinozaki","Augmented Adversarial Self-Supervised Learning for Early-Stage Alzheimer’s Speech Detection","INTERSPEECH 2022",,,,,"pp. 541-545",2022,Sept.
"Takafumi Moriya,Hiroshi Sato,Tsubasa Ochiai,Marc Delcroix,Takahiro Shinozaki","Streaming Target-Speaker ASR with Neural Transducer","INTERSPEECH 2022",,,,,"pp. 2673-2677",2022,Sept.
"Bowen Zhang,Songjun Cao,Xiaoming Zhang,Yike Zhang,Long Ma,Takahiro Shinozaki","Curriculum Semi-supervised Learning for Speech Recognition Based on Self-supervised Pre-training","INTERSPEECH 2022",,,,,"pp. 2653-2657",2022,Sept.
"Longfei Yang,Sheng Li,Jiyi Li,Takahiro Shinozaki","Multi-Domain Dialogue State Tracking with Top-k Slot Self Attention","SIGDIAL 2022","Proceedings of the 23nd Annual Meeting",,,,"pp. 231-236",2022,Sept.
"Zhuo Gong,Daisuke Saito,Longfei Yang,Takahiro Shinozaki,Sheng Li,Hisashi Kawai,Nobuaki Minematsu","Self-Adaptive Multilingual ASR Rescoring with Language Identification and Unified Language Model","Odyssey 2022",,,,,"pp. 415-420",2022,July
"Ryota Komatsu,Shengzhou Gao,Wenxin Hou,Mingxin Zhang,Tomohiro Tanaka,Keisuke Toyoda,Yusuke Kimura,Kent Hino,Yu Iwamoto,Kosuke Mori,Takuma Okamoto,Takahiro Shinozaki","Automatic Spoken Language Acquisition Based on Observation and Dialogue",,"IEEE Journal of Selected Topics in Signal Processing","IEEE",,,"  1 - 13",2022,July
"Takafumi Moriya,Takanori Ashihara,Atsushi Ando,Hiroshi Sato,Tomohiro Tanaka,Kohei Matsuura,Ryo Masumura,Marc Delcroix,Takahiro Shinozaki","Hybrid RNN-T/Attention-Based Streaming ASR with Triggered Chunkwise Attention and Dual Internal Language Model Integration","IEEE ICASSP","ICASSP",,,,"pp. 8282-8286",2022,May
"Yu Iwamoto,Takahiro Shinozaki","wav2vec 2.0 の疑似音素分割と特徴量抽出を利用したES-KMeans による教師なし音声単語発見","日本音響学会2022年春季研究発表会","日本音響学会2022年春季研究発表会講演論文集",,,,"  1-3P-1",2022,Apr.
"Keisuke Toyoda,Takahiro Shinozaki","質問音声に含まれる論理概念を理解する音声言語獲得エージェント","日本音響学会2022年春季研究発表会","日本音響学会2022年春季研究発表会講演論文集",,,,"  2-3Q-6",2022,Mar.
"Ryota Komatsu,Keisuke Toyoda,Yusuke Kimura,Kosuke Mori,Meikin Cyou,Kent Hino,Takahiro Shinozaki","OpenAI gym を用いた音声言語獲得ツールキット","日本音響学会2022年春季研究発表会","日本音響学会2022年春季研究発表会講演論文集",,,,"  1-8-7",2022,Mar.
"Tomohiro Tanaka,Ryota Komatsu,Takuma Okamoto,Takahiro Shinozaki","Pronunciation Adaptive Self Speaking Agent Using WaveGrad","AAAI-SAS","AAAI-SAS 2022",,,,"  8 pages",2022,Feb.
"Keisuke Toyoda,Takahiro Shinozaki","論理否定を含む質問音声を理解する音声言語獲得エージェント","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"  2021-SLP-139","No. 2","pp. 1 - 4",2021,Dec.
"Yu Iwamoto,Takahiro Shinozaki","Unsupervised Spoken Term Discovery Using wav2vec 2.0","APSIPA2021",,,,,"pp. 1082-1086",2021,Dec.
"Xingrui Wang,Bowen Zhang,Takahiro Shinozaki","Low-resource Mandarin Prosodic Structure Prediction Using Self-training","APSIPA2021",,,,,"pp. 859-862",2021,Dec.
"Kosuke Mori,Takahiro Shinozaki","多言語事前学習と敵対的学習による非ネイティブ英語音声認識","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"  2021-SLP-139","No. 12","pp. 1 - 5",2021,Dec.
"Wenxin Hou,Han Zhu,Yidong Wang,Jindong Wang,Tao Qin,Renjun Xu,Takahiro Shinozaki","Exploiting Adapters for Cross-Lingual Low-Resource Speech Recognition",,"IEEE/ACM Transactions on Audio, Speech, and Language Processing","IEEE","Vol. 30",,"pp. 317 - 329",2021,Dec.
"Bowen Zhang,Yidong Wang,Wenxin Hou,Hao Wu,Jindong Wang,Manabu Okumura,Takahiro Shinozaki","FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling","NeurIPS 2021",,,,,,2021,Dec.
"Keisuke Toyoda,Yusuke Kimura,Mingxin Zhang,Kent Hino,Kosuke Mori,Takahiro Shinozaki","SELF-SUPERVISED SPOKEN QUESTION UNDERSTANDING AND SPEAKING WITH AUTOMATIC VOCABULARY LEARNING","Conference of the Oriental COCOSDA 2021",,,,,"pp. 37-42",2021,Nov.
"Wenxin Hou,Jindong Wang,Xu Tan,Tao Qin,Takahiro Shinozaki","Cross-Domain Speech Recognition with Unsupervised Character-Level Distribution Matching","Interspeech2021",,,,,"pp. 3425-3429",2021,Sept.
"Tomohiro Tanaka,岡本拓磨,Takahiro Shinozaki","音声言語獲得システムのためのWaveGradを用いた音声発声機構と発音適応","日本音響学会2021年秋季研究発表会","日本音響学会2021年秋季研究発表会講演論文集",,,,"  3-3-17",2021,Sept.
"Longfei Yang,Kaiqi Fu,Jinsong Zhang,Takahiro Shinozaki","Non-native acoustic modeling for mispronunciation verification based on language adversarial representation learning",,"Neural Networks",,"volume 142",,"pp. 597--607",2021,July
"Wenxin Hou,Yidong Wang,Shengzhou Gao,Takahiro Shinozaki","Efficient Cross-Lingual Adaptation With Meta-Learning","IEEE ICASSP2021",,,,,"pp. 7028-7032",2021,June
"Tsune Kobayashi,Daisuke Matsuura,Takahiro Shinozaki","機械要素とロボティクスを核とした革新的技術の開発を目指して",,"精密工学会誌",,"Vol. 87","No. 4","pp. 363-364",2021,Apr.
"Kosuke Mori,Wenxin Hou,Takahiro Shinozaki","多言語モデルの転移学習による日本人英語音声認識","言語処理学会第27回年次大会","言語処理学会第27回年次大会予稿集",,,"  E2-3",,2021,Mar.
"Takahiro Shinozaki,Hayato Shibata,Mingxin Zhang","ハイブリッドオートエンコーダの強化学習による物理音声合成器の制御","日本音響学会2021年春季研究発表会","日本音響学会2021年春季研究発表会講演論文集",,,"  2-2-12",,2021,Mar.
"Tomohiro Tanaka,Takahiro Shinozaki","Unsupervised Sound Source Localization From Audio-Image Pairs Using Input Gradient Map","ICPR2020",,,,,,2021,Jan.
"Hayato Shibata,Mingxin Zhang,Takahiro Shinozaki","Unsupervised Acoustic-To-Articulatory Inversion Neural Network Learning Based on Deterministic Policy Gradient","IEEE Spoken Language Technology2021",,"IEEE",,,"pp. 530-537",2021,Jan.
"Takahiro Shinozaki,Mingxin Zhang,Tomohiro Tanaka,Wenxin Hou,Shengzhou Gao","音声画像グラウンディングに基づいた注意機構による効率的な音声言語獲得","計測自動制御学会 システム・情報部門 学術講演会 2020","計測自動制御学会 システム・情報部門 学術講演会 2020予稿集",,,"  GS2-4-5",,2020,Nov.
"Takahiro Shinozaki,Shengzhou Gao,Wenxin Hou,Tomohiro Tanaka","連続音声からの教師なし単語辞書学習に基づく言語獲得エージェント","計測自動制御学会 システム・情報部門 学術講演会 2020","計測自動制御学会 システム・情報部門 学術講演会 2020予稿集",,,"  GS2-4-4",,2020,Nov.
"Takahiro Shinozaki,Shengzhou Gao,Mingxin Zhang,Wenxin Hou,Tomohiro Tanaka","言語獲得能力を備えた音声対話エージェントの検討","第57回人工知能学会 AI チャレンジ研究会","第57回人工知能学会 AI チャレンジ研究会予稿集",,,"  SIG-Challenge-057-13",,2020,Nov.
"Mingxin Zhang,Tomohiro Tanaka,Wenxin Hou,Shengzhou Gao,Takahiro Shinozaki","Sound-Image Grounding Based Focusing Mechanism for Efficient Automatic Spoken Language Acquisition","Interspeech 2020",,,,,,2020,Oct.
"Wenxin Hou,Yue Dong,Bairong Zhuang,Longfei Yang,Jiatong Shi,Takahiro Shinozaki","Large-Scale End-to-End Multilingual Speech Recognition and Language Identification with Multi-Task Learning","Interspeech 2020",,,,,,2020,Oct.
"Jianshu Zhao,Shengzhou Gao,Takahiro Shinozaki","Time-Domain Target-Speaker Speech Separation With Waveform-Based Speaker Embedding","Interspeech 2020",,,,,,2020,Oct.
"Longfei Yang,Kaiqi Fu,Jinsong Zhang,Takahiro Shinozaki","Pronunciation Erroneous Tendency Detection with Language Adversarial Represent Learning","Interspeech 2020",,,,,,2020,Oct.
"Hou Wenxin,Yue Dong,Bairong Zhuang,楊 龍飛,Shi Jiatong,Takahiro Shinozaki","超多言語事前学習による低資源音声認識の検討","日本音響学会","日本音響学会2020年秋季研究発表会講演論文集",,,"  2-P1-7",,2020,Sept.
"Kent Hino,Takahiro Shinozaki","Transformer 音声認識システムの進化的最適化","日本音響学会","日本音響学会2020年秋季研究発表会講演論文集",,"  2-P1-6",,,2020,Sept.
"Takahiro Shinozaki,Shengzhou Gao,Mingxin Zhang,Wenxin Hou,Tomohiro Tanaka","相乗的複合学習による効率的な音声言語獲得機構","人工知能学会 第89回 言語・音声理解と対話処理研究会","第89回 言語・音声理解と対話処理研究会資料集",,,"No. 11",,2020,Sept.
"Shengzhou Gao,Wenxin Hou,Tomohiro Tanaka,Takahiro Shinozaki","SPOKEN LANGUAGE ACQUISITION BASED ON REINFORCEMENT LEARNING AND WORD UNIT SEGMENTATION","日本音響学会","日本音響学会2020年秋季研究発表会講演論文集",,,"  3-2-8",,2020,Sept.
"Kent Hino,Yusuke Kimura,Yue Dong,Takahiro Shinozaki","Dual Inheritance Evolution Strategy for Deep Neural Network Optimization","Proc. IEEE Congress on Evolution Computation (CEC)",,"IEEE",,,,2020,July
"Shengzhou Gao,Wenxin Hou,Tomohiro Tanaka,Takahiro Shinozaki","Spoken Language Acquisition Based on Reinforcement Learning and Word Unit Segmentation","ICASSP2020",,,,,"pp. 6144-6148",2020,May
"Takahiro Shinozaki,Shinji Watanabe,Kevin Duh","Automated Development of DNN Based Spoken Language Systems Using Evolutionary Algorithms",,"Deep Neural Evolution - Deep Learning with Evolutionary Computation","Hitoshi Iba",,,"pp. 97-129",2020,May
"Takahiro Shinozaki","スピーキングの自動採点技術はどの程度進んでいるか",,"教材・テスト作成のためのCEFR-Jリソースブック","大修館書店",,,"pp. 148-153",2020,Apr.
"Kent Hino,Yusuke Kimura,Yue Dong,Takahiro Shinozaki","二重相続進化戦略による音声認識システムの最適化","日本音響学会","日本音響学会2020年春季研究発表会講演論文集",,"  2-4-5",,"pp. 893-894",2020,Mar.
"Takahiro Shinozaki","音声認識の現状と将来","日本シミュレーション学会","シミュレーション",,"Vol. 39","No. 1",,2020,Mar.
"Tomohiro Tanaka,Takahiro Shinozaki","CNNフロントエンドによる高速なEnd-to-End連続DPマッチングの実現","日本音響学会","日本音響学会2020年春季研究発表会講演論文集",,"  2-4-4",,"pp. 891-892",2020,Mar.
"Chonghui Zheng,Takahiro Shinozaki","Robust Multichannel End-to-End Speech Recognition Based on Multi-Output Densenet","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"  2020-SLP-131","No. 10","pp. 1-3",2020,Feb.
"Yusuke Kimura,Kent Hino,Yue Dong,Takahiro Shinozaki","二重相続進化戦略によるEnd-to-End音声認識システムの最適化","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"  2020-SLP-131","No. 11","pp. 1-3",2020,Feb.
"Tomohiro Tanaka,Takahiro Shinozaki","Efficient free keyword detection based on cnn and end-to-end continuous dp-matching","2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)",,,,,"pp. 637-644",2019,Dec.
"Tomohiro Tanaka,Takahiro Shinozaki","CNNフロントエンドによるEnd-to-End連続DPマッチングの高速化","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"Vol. 2019-SLP-130","No. 2","pp. 1 - 4",2019,Dec.
"Yi Liu,Bairong Zhuang,Zhiyu Li,Takahiro Shinozaki","Cross-Domain Speaker Recognition using Cycle-Consistent Adversarial Networks","2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)",,,,,"pp. 2070-2074",2019,Nov.
"Takekatsu Hiramura,Takahiro Shinozaki","営業電話における大規模 End-to-End 音声認識システムの活用","日本音響学会","日本音響学会2019年秋季研究発表会講演論文集",,"  1-3-3",,"pp. 1183-1184",2019,Sept.
"Tomohiro Tanaka,Takahiro Shinozaki","入力画像勾配を用いたモデル構造フリーな教師無し音源ローカライゼーション","日本音響学会","日本音響学会2019年秋季研究発表会講演論文集",,"  2-3-3",,"pp. 919-920",2019,Sept.
"Takahiro Shinozaki","Deep neural network optimization based on dual inheritance theory and its application","学際大規模情報基盤共同利用・共同研究拠点 第11回シンポジウム",,,"Vol. jh190066-DAH",,,2019,July
"Takahiro Shinozaki","Automated Development of Deep Neural Network Systems Based on Evolutionary Algorithms","Third International Workshop on Symbolic-Neural Learning (SNL-2019)",,,,,,2019,July
"Xu Han,Takahiro Shinozaki,Ryota Kobayashi","Effective and Stable Neuron Model Optimization Based on Aggregated CMA-ES","2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",,,,,"pp. 1264-1268",2019,May
"Tomohiro Tanaka,Takahiro Shinozaki","連続単語検出のための 2D-RNN を用いた End-to-EndDPマッチング","日本音響学会2019年春季研究発表会","日本音響学会2019年春季研究発表会講演論文集",,,"  2-P-13","pp. 979-980",2019,Mar.
"Yilong Peng,Takahiro Shinozaki","大規模 End-to-End 音声認識システムの教師なし強化学習の実現に向けた検討","日本音響学会2019年春季研究発表会","日本音響学会2019年春季研究発表会講演論文集",,,"  1-P-9","pp. 919-920",2019,Mar.
"Wenbo Wang,Bairong Zhuang,Takahiro Shinozaki","Analysis of Attention-Based Multimodal Fusion and Maximum Mutual Information Objective for DSTC7 Audio Visual Scene-Aware Dialog Track","日本音響学会2019年春季研究発表会案内","日本音響学会2019年春季研究発表会講演論文集",,,"  2-P-10","pp. 973-974",2019,Mar.
"Tomohiro Tanaka,Takahiro Shinozaki","連続対応検出ネットワークによる音声動画からの教師なし物体セグメンテーションおよび関連学習の検討","日本音響学会2019年春季研究発表会","日本音響学会2019年春季研究発表会講演論文集",,,"  2-P-13","pp. 979-980",2019,Mar.
"Xu Han,Takahiro Shinozaki,Ryota Kobayashi","Aggregated CMA-ES: An Effective and Stable Strategy for Neuron Model Optimization","バイオ情報学研究会",,,,"No. 9","pp. 1-2",2019,Mar.
"Yi Liu,Takahiro Shinozaki","I-vector  Domain  Adaptation  Using  Cycle-Consistent  Adversarial  Networks  for  Speaker Recognition","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"  2019-SLP-126","No. 2","pp. 1-3",2019,Feb.
"Takafumi Moriya,Tomohiro Tanaka,Takahiro Shinozaki,Shinji Watanabe,Kevin Duh","Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition",,"IEEE/ACM Transactions on Audio, Speech, and Language Processing",,"Vol. 27","No. 1","pp. 77-88",2019,Jan.
"Takahiro Shinozaki","自動音声認識技術と英語教育：仕組みと研究動向、いまできること・できないこと",,"英語教育","大修館書店","  2019年2月号","  第2特集",,2019,Jan.
"Bairong Zhuang,Wenbo Wang,Takahiro Shinozaki","Investigation of Attention-Based Multimodal Fusion and Maximum Mutual Information Objective for DSTC7 Track3","DSTC7",,,,,,2019,Jan.
"Wenbo Wang,Bairong Zhuang,Takahiro Shinozaki","Improving the audio visual scene-aware dialog system in DSTC7 by using attentional multimodal fusion and MMI objective","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"  2018-SLP-125","No. 12","pp. 1-3",2018,Dec.
"Tomohiro Tanaka,Takahiro Shinozaki","マルチゲートGRUユニットを用いた2D-RNNによるEnd-to-End始終端フリー単語検出","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"  2018-SLP-125","No. 5","pp. 1-3",2018,Dec.
"Yilong Peng,Hayato Shibata,Takahiro Shinozaki","Reward Only Training of Encoder-Decoder Digit Recognition Systems Based on Policy Gradient Methods","APSIPA ASC",,"IEEE",,,"pp. 1934-1939",2018,Nov.
"Tomohiro Tanaka,Takahiro Shinozaki","F-Measure Based End-To-End Optimization of Neural Network Keyword Detectors","APSIPA ASC",,"IEEE",,,"pp. 1456-1461",2018,Nov.
"Tomohiro Tanaka,Takahiro Shinozaki","単語検出性能を目的関数とした単語検出器学習法の提案",,"2018年秋季研究発表会",,,,,2018,Sept.
"Yilong Peng,Hayato Shibata,Takahiro Shinozaki","音声認識システムの教師なし強化学習における報酬と報酬ノイズの影響の検討","2018年秋季研究発表会",,,,,,2018,Sept.
"Hayato Shibata,Yilong Peng,Takahiro Shinozaki","強化学習による報酬のみを用いたend-to-end 認識システム学習","2018年秋季研究発表会",,,,,,2018,Sept.
"Yilong Peng,Hayato Shibata,Takahiro Shinozaki","End-to-end音声認識システムの強化学習の検討","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"  2018-SLP-123","No. 9","pp. 1-4",2018,July
"Ukrish Vanichrujee,Teerayut Horanont,Thanaruk Theeramunkong,Wasan Pattara-atikom,Takahiro Shinozaki","Taxi Demand Prediction using Ensemble Model Based on RNNs and XGBOOST","9th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES)","9th International Conference of Information and Communication Technology for Embedded Systems",,,,"pp. 130-135",2018,May
"Taku Kato,Takahiro Shinozaki","Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection","IEEE ICASSP 2018",,"IEEE",,,"pp. 5759-5763",2018,Apr.
"Taku Kato,Takahiro Shinozaki","方策勾配法と仮説選択に基づくDNN音声認識システムの強化学習","日本音響学会","春季研究発表会講演論文集",,,,,2018,Mar.
"鄭 崇輝,李 知雨,王 文博,庄 佰融,Takahiro Shinozaki","End-to-Endニューラル対話モデルにおける単語分散表現の比較検討","日本音響学会","2018年春季研究発表会講演論文集",,,,,2018,Mar.
"Takahiro Shinozaki,Taku Kato","日本人英語学習者を対象とした自動英語音声認識の予備検討","CEFR-J 2018 Symposium",,,,,,2018,Mar.
"Yuki Ikeshita,Takahiro Shinozaki","音声認識仮説を用いたベイズ的半教師あり発音辞書学習の検討","日本音響学会","春季研究発表会講演論文集",,,,,2018,Mar.
"Fuming Fang,Takahiro Shinozaki","Electrooculography-based continuous eye-writing recognition system for efficient assistive communication systems",,,"Pros One",,,,2018,Feb.
"Hayato Shibata,Taku Kato,Takahiro Shinozaki,Shinji Watanabe","Composite Embedding Systems for Zerospeech2017 Track1","IEEE ASRU","Proc. IEEE ASRU 2017",,,,"pp. 747-753",2017,Dec.
"Hao Qin,Takahiro Shinozaki,Kevin Duh","Evolution Strategy Based Automatic Tuning of Neural Machine Translation Systems","IWSLT","Proc. International Workshop on Spoken Language Translation",,,,"pp. 120-128",2017,Dec.
"Taku Kato,Takahiro Shinozaki","英語学習者の発声自動評価を目的としたDNN音声認識システムの検討","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"Vol. 2017-SLP-119","No. 11","pp. 1-4",2017,Dec.
"Zhuang Bairong,Wang Wenbo,Li Zhiyu,Zheng Chonghui,Takahiro Shinozaki","Comparative Analysis of Word Embedding Methods for DSTC6 End-to-End Conversation Modeling Track[C]","Proc. Dialog System Technology Challenges  (DSTC6)",,,,,,2017,Dec.
"Yuki Ikeshita,Takahiro Shinozaki,渡部晋治,持橋大地,Graham Neubig","ベイズ推論を用いた半教師あり学習の日本語適用","情報処理学会 音声言語情報処理研究会 SIG-SLP","情報処理学会 音声言語情報処理研究会 SIG-SLP",,"Vol. 2017-SLP-118","No. 3","pp. 1-4",2017,Oct.
"Taku Kato,Takahiro Shinozaki","仮説選択に基づくDNN音声認識システムの強化学習","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"Vol. 2017-SLP-118","No. 4","pp. 1-5",2017,Oct.
"Hayato Shibata,Taku Kato,Takahiro Shinozaki,渡部晋治","ゼロリソース言語への応用を目的としたABXテストによるDNN特徴量の検討","日本音響学会","秋季研究発表会講演論文集",,,,"pp. 1-2",2017,Sept.
"覃 浩,Takahiro Shinozaki,Duh Kevin","進化的戦略を用いたニューラル機械翻訳システムの自動最適化","日本音響学会","2017年秋季研究発表会講演論文集",,,,"pp. 1397-1398",2017,Sept.
"銭 博宇,Jian Wang,劉 溢,Kai Zhu,Takahiro Shinozaki","進化的戦略を用いたDNNハードウエア音声センサの低消費電力化","日本音響学会","2017年秋季研究発表会講演論文集",,,,"pp. 131-132",2017,Sept.
"Takahiro Shinozaki,Shinji Watanabe,Daichi Mochihashi,Graham Neubig","Semi-Supervised Learning of a Pronunciation Dictionary from Disjoint Phonemic Transcripts and Text","Interspeech",,,,,,2017,Aug.
"Yusuke Yamada,Takashi Nose,Yuya Chiba,Akinori Ito,Takahiro Shinozaki","Development and Evaluation of Julius-Compatible Interface for Kaldi ASR","The Thirteenth International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP)",,,,,,2017,Aug.
"Kazuki Sato,Takashi Nose,Akira Ito,Yuya Chiba,Akinori Ito,Takahiro Shinozaki","A Study on 2D Photo-Realistic Facial Animation Generation Using 3D Facial Feature Points and Deep Neural Networks","The Thirteenth International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP)",,,,,,2017,Aug.
"Yi Liu,Boyu Qian,Jian Wang,Takahiro Shinozaki","Hardware Speech Sensor Based on Deep Neural Network Feature Extractor and Template Matching","音声研究会(SP)",,,,,"pp. 297-300",2017,Mar.
"Takahiro Shinozaki","HMMについてやさしく教えてください",,"音響学入門ペディア","コロナ社",,,"pp. 116-119",2017,Mar.
"Takahiro Shinozaki,渡部晋治,持橋大地,Graham Neubig","ベイズ的教師なし発音辞書学習のWFST実装およびサンプリングアルゴリズムの検討",,"日本音響学会春季研究発表会講演論文集",,,,"pp. 17-18",2017,Mar.
"Tomohiro Tanaka,Takahiro Shinozaki,渡部晋治","Highwayネットワーク言語モデルを用いた日本語話し言葉音声認識",,"日本音響学会春季研究発表会講演論文集",,,,"pp. 107-108",2017,Mar.
"Taku Kato,Takahiro Shinozaki","半教師ありDNN学習を用いた日本語スピーキングテスト音声の認識",,"日本音響学会春季研究発表会講演論文集",,,,"pp. 93-94",2017,Mar.
"Takahiro Shinozaki,小池治憲,Takashi Nose,Akinori Ito","読み上げ音声を用いたニューラルネットワークによる任意歌唱者歌声声質変換の検討",,"日本音響学会春季研究発表会講演論文集",,,,"pp. 357-358",2017,Mar.
"Takahiro Shinozaki,宮本 颯,Takashi Nose,伊藤鈴乃介,小池治憲,Akinori Ito","敵対的学習を利用したニューラルネットワークに基づく任意話者声質変換の検討",,"日本音響学会春季研究発表会講演論文集",,,,"pp. 355-356, 357-358",2017,Mar.
"王 健,銭 博宇,劉溢,Takahiro Shinozaki","進化戦略に基づいた単語検出ハードウェアのためのDNNメタパラメータ最適化","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"Vol. 2017-SLP-115","No. 6","pp. 1-4",2017,Feb.
"Natsumi Ozawa,Tomohiro Tanaka,Takahiro Shinozaki","ChimeChallengeタスクにおけるNMFによる雑音除去の検討","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"Vol. 2017-SLP-115","No. 12","pp. 1-4",2017,Feb.
"Takahiro Shinozaki,渡部晋治,持橋大地,Graham Neubig","第３回Frederick Jelinek記念サマーワークショップでの教師なし発音辞書学習の取り組み","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"  2016-SLP-114","No. 4","pp. 1-5",2016,Dec.
"Tomohiro Tanaka,Takahiro Shinozaki,Shinji Watanabe,Takaaki Hori","Automated Structure Discovery and Parameter Tuning of Neural Network Language Model based on Evolution Strategy","Spoken Language Technology (SLT)",,,,,"pp. 665-671",2016,Dec.
"Fuming Fang,Takahiro Shinozaki","眼球動作に基づいた対話支援システムのための連続画なぞり入力手法","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"Vol. 2016-SLP-114","No. 19","pp. 1-6",2016,Dec.
"Koike Harunori,Takashi Nose,Takahiro Shinozaki,Akinori Ito","Improvement of quality of voice conversion based on spectral differential filter using STRAIGHT-based mel-cepstral coefficients","ASJ and ASA joint meeting","Journal of the Acoustical Sciety of America",,,,,2016,Nov.
"Tomohiro Tanaka,Takafumi Moriya,Takahiro Shinozaki,Shinji Watanabe,Takaaki Hori,Kevin duh","Evolutionary optimization of Long Short-Term Memory neural network language model","ASJ and ASA joint meeting (Journal of the Acoustical Sciety of America",,,,,"pp. 3062",2016,Nov.
"Taku Kato,Takahiro Shinozaki","日本語話し言葉音声における半教師ありDNN学習の検討","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,"Vol. 2016-SLP-113","No. 1","pp. 1-6",2016,Oct.
"Takahiro Shinozaki","大規模進化計算による音声認識システム開発の自動化","GTC Japan 2016",,,,,,2016,Oct.
"Takahiro Shinozaki","Kaldiツールキットを用いた音声認識システムの構築","音声研究会",,,,,,2016,Oct.
"Yuki Ikeshita,Takahiro Shinozaki","連続音声認識におけるLSTMによる単語履歴を考慮した未知語検出法","日本音響学会秋季研究発表会",,,,,,2016,Sept.
"Tomohiro Tanaka,Takafumi Moriya,Takahiro Shinozaki,渡部晋治,堀貴明,Kevin Duh","進化的戦略を用いたリカレントニューラルネットワーク言語モデルの最適化",,"日本音響学会秋季研究発表会講演論文集",,,,"pp. 31-32",2016,Sept.
"Tomohiro Tanaka,Takahiro Shinozaki,Shinji Watanabe,Takaaki Hori","Evolution Strategy Based Neural Network Optimization and LSTM Language Model for Robust Speech Recognition","4th International Workshop on Speech Processing in Everyday Environments CHiME 2016",,,,,,2016,Sept.
"Fuming Fang,Takahiro Shinozaki,Yasuo Horiuchi,Shingo Kuroiwa,Sadaoki Furui,Toshimitsu Musha","Improving eye motion sequence recognition using electrooculography based on context-dependent HMM",,"Computational Intelligence and Neuroscience",,,,,2016,Sept.
"Takahiro Shinozaki","音声認識ツールキットKaldiを用いた大語彙日本語音声認識","FIT2016",,,,,,2016,Sept.
"小池治憲,Takashi Nose,Takahiro Shinozaki,Akinori Ito","差分スペクトルフィルタに基づく声質変換における性能向上の検討",,"日本音響学会秋季研究発表会講演論文集",,,,"pp. 285-286",2016,Sept.
"Yuki Ikeshita,Takahiro Shinozaki","LSTMによる単語履歴を考慮した未知語検出法","音声研究会(SP)",,,,,"pp. 33-36",2016,Aug.
"峯松信明,秋田祐哉,浅見太一,伊藤信貴,落合翼,Tomoki Koriyama,齋藤大輔,塩田さやか,Takahiro Shinozaki,鈴木雅之,高木信二,俵直弘,橋本佳,樋口卓哉,福田隆","国際会議ICASSP2016参加報告",,"研究報告音声言語情報処理（SLP）","情報処理学会","Vol. 2016-SLP-112","No. 5","pp. 1-6",2016,July
"小池治憲,Takashi Nose,Takahiro Shinozaki,Akinori Ito","声質変換における学習時の DTW 精度が性能に与える影響","日本音響学会","春季研究発表会講演論文集",,,,"pp. 313-314",2016,Mar.
"Takafumi Moriya,Tanaka Tomohiro,Takahiro Shinozaki,渡部晋治,Duh Kevin","進化的戦略による高精度大語彙音声認識システムの多目的最適化",,"春季研究発表会講演論文集",,,,"pp. 45-46",2016,Mar.
"小池治憲,Takashi Nose,Takahiro Shinozaki,Akinori Ito","入力話者非依存ニューラルネットワークに基づく差分スペクトルフィルタを用いた声質変換における学習データ量の影響","日本音響学会","春季研究発表会講演論文集",,,,"pp. 241-242",2016,Mar.
"Tomohiro Tanaka,Takafumi Moriya,Takahiro Shinozaki,渡部晋治,堀貴明","Kaldi 用 CSJ レシピへの RNN 言語モデルの導入と性能評価","日本音響学会","春季研究発表会講演論文集",,,,"pp. 193-194",2016,Mar.
"Takahiro Shinozaki,Takafumi Moriya,Tomohiro Tanaka,渡部晋治","KaldiにおけるCSJレシピの利用法","音声言語情報処理研究会",,,"  2016-SLP-110","No. 8","pp. 1-6",2016,Feb.
"Ryo Hakataya,Takahiro Shinozaki,Tomoki Koriyama","粒子フィルタとガウス過程回帰によるシングルチャネル音源分離","情報処理学会 音声言語情報処理研究会 SIG-SLP",,"情報処理学会","Vol. 2016-SLP-110","No. 6","pp. 1-6",2016,Feb.
"Saito, Y.,Nose, T.,Takahiro Shinozaki,Ito, A.","Conversion of Speaker's Face Image Using PCA and Animation Unit for Video Chatting",,"Proceedings - 2015 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2015",,,,"pp. 433-436",2016,
"akafumi Moriya,Tomohiro Tanaka,Takahiro Shinozaki,Shinji Watanabe,Kevin Duh","Automation of System Building for State-of-the-art Large Vocabulary Speech Recognition Using Evolution Strategy","IEEE 2015 Automatic Speech Recognition and Understanding Workshop (ASRU)",,,,,"pp. 610-616",2015,Dec.
"Takahiro Shinozaki,Takafumi Moriya,田中智大・篠崎隆宏,渡部晋治,Kevin","パレート最適と進化的戦略を用いた高精度大語彙音声認識システム構築の自動化",,,,,,"pp. 31-36",2015,Dec.
"Kai Zhu,李昊霖,Takahiro Shinozaki,Yasuo Horiuchi,黒岩眞吾","DNN特徴量抽出器に基づく単語検出器のFPGA実装と評価","日本音響学会","秋季研究発表会講演論文集",,,,"pp. 153-154",2015,Sept.
"Takafumi Moriya,Takahiro Shinozaki,渡部晋治","高精度日本語話し言葉音声認識のためのKaldiレシピとその評価","日本音響学会","秋季研究発表会講演論文集",,,,"pp. 155-156",2015,Sept.
"岡本拓磨,小川哲司,落合翼,柏木陽佑,亀岡弘和,木下慶介,Tomoki Koriyama,齋藤大輔,Takahiro Shinozaki,高木信二,滝口哲也,太刀岡勇気,俵直弘,橋本佳,藤本雅清,松田繁樹,三村正人,吉岡拓也,渡部晋治","国際会議ICASSP2015参加報告",,"研究報告音声言語情報処理（SLP）","情報処理学会","Vol. 2015-SLP-107","No. 3","pp. 1-7",2015,July
"齋藤優貴,Takashi Nose,Takahiro Shinozaki,Akinori Ito","ビデオ通話における音声および表情特徴量を用いた話者変換の検討","EMM研究会",,,,,,2015,May
"Kai Zhu,Takahiro Shinozaki","DNN特徴量抽出器とDTWによる組み込みシステム向け耐雑音単語検出器の検討","日本音響学会","春季研究発表会講演論文集",,,,"pp. 155-156",2015,Mar.
"齋藤優貴,Takashi Nose,Takahiro Shinozaki,Akinori Ito","ビデオ通話におけるニューラルネットワークを利用した話者変換の検討","情報処理学会","情報処理学会第77回全国大会論文集",,,,,2015,Mar.
"Takahiro Shinozaki,渡部 晋治","進化的アルゴリズムの大規模実行によるDNN構造最適化","日本音響学会","春季研究発表会講演論文集",,,,"pp. 11-12",2015,Mar.
"yojiro ito,Takahiro Shinozaki,Takashi Nose","ニューラルネットワークを用いた話者特徴量抽出に基づく一対多クロスリンガル声質変換","日本音響学会","春季研究発表会講演論文集",,,,"pp. 397-398",2015,Mar.
"Takashi Nose,Takahiro Shinozaki,yojiro ito,Akinori Ito","ニューラルネットワークに基づくユーザ音声を必要としない多対一声質変換の検討","日本音響学会","春季研究発表会講演論文集",,,,"pp. 271-274",2015,Mar.
"小野 豊,Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾","スピーキングテストシステムにおける発話内容を考慮した自動採点","電子情報通信学会",,,,,"pp. 120",2015,Mar.
"Rina Mashiko,Tomoki Koriyama,Takahiro Shinozaki,Takao Kobayashi","言語モデルと音響モデルを用いた自動韻律ラベリングの評価","日本音響学会2015年春季研究発表会","日本音響学会2015年春季研究発表会講演論文集","日本音響学会",,,"pp. 361-362",2015,Mar.
"Takahiro Shinozaki,Watanabe, S.","Structure discovery of deep neural network based on evolutionary algorithms",,"ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",,"Vol. 2015-August",,"pp. 4979-4983",2015,
"yojiro ito,Takahiro Shinozaki,Takashi Nose","話者特徴量入力を付加したデノイジングオートエンコーダによるクロスリンガル声質変換","情報処理学会 音声言語情報処理研究会 SIG-SLP",,,,,,2014,Dec.
"Takahiro Shinozaki","ディープニューラルネットワークを用いた簡素な構造の単一単語検出器の検討","日本音響学会","秋季講演論文集",,,,"pp. 149-150",2014,Sept.
"Tomoki Koriyama,Hiroshi Suzuki,Takashi Nose,Takahiro Shinozaki,Takao Kobayashi","Accent Type and Phrase Boundary Estimation Using Acoustic and Language Models for Automatic Prosodic Labeling","INTERSPEECH 2014","Proc. INTERSPEECH 2014","ISCA",,,"pp. 2337-2341",2014,Sept.
"Yusuke Arao,Takashi Nose,Takahiro Shinozaki,Takao Kobayashi","複数ドメインコーパスからの文選択に基づくキャラクター音声合成の検討","日本音響学会","秋季講演論文集",,,,"pp. 351 - 352",2014,Sept.
"Tomoya Kobayashi,Takashi Nose,Takahiro Shinozaki,Takao Kobayashi","GMMに基づく声質変換のためのMDL基準による混合数の自動決定","日本音響学会","秋季講演論文集",,,,"pp. 341-342",2014,Sept.
"Fuming Fang,Takahiro Shinozaki,古井 貞煕,Yasuo Horiuchi,黒岩 眞吾","眼電位入力音声合成インタフェースのためのコンテキスト依存眼動素を用いた眼電位認識","日本音響学会","秋季講演論文集",,,,"pp. 393-394",2014,Sept.
"小宮山 大樹,Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾","Denoising Autoencoderによる残響除去の大語彙音声認識における評価","日本音響学会","秋季講演論文集",,,,"pp. 131-132",2014,Sept.
"Fuming Fang,Takahiro Shinozaki,Takao Kobayashi","スイッチ入力音声コミュニケーション支援システムのための入力プロトコル推薦手法","日本音響学会","秋季研究発表会講演論文集",,,,"pp. 229-230",2014,Sept.
"Ryo Hakataya,Takahiro Shinozaki,Takao Kobayashi","ボルツマンマシンとMCMCサンプリングを用いた音声のシングルチャネル雑音除去","日本音響学会","秋季研究発表会講演論文集",,,,"pp. 59-60",2014,Sept.
"Fuming Fang,Takahiro Shinozaki,Takao Kobayashi","スイッチ入力音声合成システムのための仮名プロトコル推薦手法",,"電子情報通信学会技術研究報告 = IEICE technical report : 信学技報","一般社団法人電子情報通信学会","Vol. 114","No. 52","pp. 355-360",2014,May
"Hiroshi Suzuki,Tomoki Koriyama,Takashi Nose,Takahiro Shinozaki,Takao Kobayashi","音響モデルと言語モデルを利用したアクセント型・アクセント句境界の同時推定","日本音響学会2014年春季研究発表会","日本音響学会2014年春季研究発表会講演論文集","日本音響学会",,,"pp. 441-442",2014,Mar.
"Eiki Tateno,Takashi Nose,Tomoki Koriyama,Takahiro Shinozaki,Takao Kobayashi","HMM音声合成のための音節出現頻度にロバストな音素セットの検討","日本音響学会2014年春季研究発表会","日本音響学会2014年春季研究発表会講演論文集","日本音響学会",,,"pp. 409-410",2014,Mar.
"Yusuke Arao,Takashi Nose,Tomoki Koriyama,Takahiro Shinozaki,Takao Kobayashi","音声合成のための音韻・韻律コンテキストを考慮した文選択アルゴリズムの評価","日本音響学会2014年春季研究発表会","日本音響学会2014年春季研究発表会講演論文集","日本音響学会",,,"pp. 405-406",2014,Mar.
"Takahiro Shinozaki,Masakazu Sekijima","SCMS2.0によるタンパク質ポテンシャルエネルギー最小化の諸条件における評価","バイオ情報学研究発表会",,,,,,2014,Mar.
"永谷 悠,李 昊霖,Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾","ハードウエア音声認識研究のためのプラットフォームFPGA基板","日本音響学会","春季講演論文集",,,,"pp. 185-186",2014,Mar.
"山本 宗典,Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾","腕時計型スマートデバイスにおける音声GUIの有効性の検討","日本音響学会","春季講演論文集",,,,"pp. 147-148",2014,Mar.
"河原達也,Koichi Shinoda,堀貴明,堀智織,Takahiro Shinozaki","「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",2014,Jan.
"Fang, F.,Takahiro Shinozaki,Takao Kobayashi","An automatic input protocol recommendation method for tailored switch-to-speech communication aid systems",,"2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014",,,,,2014,
"Lu, H.,Yamada, T.,Imai, S.,Takahiro Shinozaki,Nisimura, R.,Ishizuka, K.,Makino, S.,Kitawaki, N.","Automatic scoring method for open answer task in the SJ-CAT speaking test considering utterance difficulty level",,"2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014",,,,,2014,
"Hiroshi Suzuki,Tomoki Koriyama,Takashi Nose,Takahiro Shinozaki,Takao Kobayashi","言語モデルと音響モデルを利用したアクセント境界の自動推定",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 113","No. 366","pp. 97-102",2013,Dec.
"Tomohisa Kawasaki,Takahiro Shinozaki,Sadaoki Furui","Direct manipulation interface for 3D agents based on stretched word-end voice commands",,"IEEJ Transactions on Electronics, Information and Systems",,"Vol. 133","No. 12","pp. 2257-2263",2013,Dec.
"Felipe Gomez-Caballero,Takahiro Shinozaki,Sadaoki Furui,Koichi Shinoda","Statistical Person Verification Using Behavioral Patterns from Complex Human Motion","New Trends in Image Analysis and Processing ICIAP 2013","New Trends in Image Analysis and Processing ICIAP 2013",,,,"pp. 550-558",2013,Sept.
"Takahiro Shinozaki,小野 豊","S-CATにおける音響特徴量とSVRによるスコア推定","日本行動計量学会",,,,,"pp. 44-45",2013,Sept.
"Felipe Gomez-Caballero,Takahiro Shinozaki,Sadaoki Furui,Koichi Shinoda","A statistical approach for person verification using human behavioral patterns",,"EURASIP Journal on Image and Video Processing 2013",,"  2013:44",,"pp. 1-11",2013,Aug.
"小宮山 大樹,石井 敬章,Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾","Denoising Autoencoderを用いた残響下大語彙音声認識の検討","情報処理学会",,,"vol. 2013-SLP-97","No. 1","pp. 1-6",2013,July
"白井 洋輔,柳村 舞衣,Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾,遠藤 俊樹,Eiji Utsunomiya","ユーザ属性を考慮した字幕付与方法の検討",,"信学技報",,"vol. 112","no. 475","pp. 245-250",2013,Mar.
"Fuming Fang,Takahiro Shinozaki,Yasuo Horiuchi,Shingo Kuroiwa,Sadaoki Furui,Toshimitsu Musha","Eye motion input based speech synthesis interface for communication aids","IEICE SIG-WIT","IEICE technical report",,,,,2013,Feb.
"Ishii, T.,Komiyama, H.,Takahiro Shinozaki,Horiuchi, Y.,Kuroiwa, S.","Reverberant speech recognition based on denoising autoencoder",,"Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",,,,"pp. 3512-3516",2013,
"Takahiro Shinozaki,Sadaoki Furui,Yasuo Horiuchi,Shingo Kuroiwa","Pipeline decomposition of speech decoders and their implementation based on delayed evaluation","2012 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","Proceedings of 2012 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference",,,,,2012,Dec.
"小野 豊,大竹 美鈴,Takahiro Shinozaki,西村 竜一,山田 武志,石塚 賢吉,Yasuo Horiuchi,黒岩 眞吾,今井 新悟","日本語スピーキングテストシステムS-CAT のためのSVR による自由発話の自動採点","日本音響学会","秋季講演論文集",,,,"pp. 335-336",2012,Sept.
"Fuming Fang,Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾,Sadaoki Furui","Continuous electrooculogram recognition for an eye-motion-based communication aid system","2012 Autumn Meeting, Acoustical Society of Japan","秋季講演論文集",,,,"pp. 1513-1514",2012,Sept.
"山畑 勇人,大久保 梨思子,山田 武志,今井 新悟,石塚 賢吉,Takahiro Shinozaki,西村 竜一,牧野 昭二,北脇 信彦","日本語スピーキングテストにおける文章読み上げ問題の自動採点の検討","日本音響学会","秋季講演論文集",,,,"pp. 399-400",2012,Sept.
"西村 竜一,栗原 理沙,Takahiro Shinozaki,石塚 賢吉,山田 武志,今井 新悟,河原 英紀,入野 俊夫","日本語スピーキングテストS-CAT における並列セグメンテーションを用いた自動採点の検討","日本音響学会","秋季講演論文集",,,,"pp. 397-399",2012,Sept.
"大久保 梨思子,山畑 勇人,山田 武志,今井 新悟,石塚 賢吉,Takahiro Shinozaki,西村 竜一,牧野 昭二,北脇 信彦","日本語スピーキングテストにおける文生成問題の自動採点の検討","日本音響学会","秋季講演論文集",,,,"pp. 395-396",2012,Sept.
"Fuming Fang,Takahiro Shinozaki,Yasuo Horiuchi,Shingo Kuroiwa,Sadaoki Furui,Toshimitsu Musha","HMM Based Continuous EOG Recognition for Eye-input Speech Interface","INTERSPEECH 2012","Proceedings of INTERSPEECH 2012",,,,,2012,Sept.
"Takahiro Shinozaki,Sadaoki Furui,Yasuo Horiuchi,Shingo Kuroiwa","Pipeline decomposition of speech recognition systems and their implementation based on delayed evaluation","2012 Autumn Meeting, Acoustical Society of Japan",,,,,,2012,Sept.
"深津 澪,Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾","純粋関数型コンパクトデコーダHusky2 の性能評価","日本音響学会","秋季講演論文集",,,,"pp. 187-188",2012,Sept.
"Tomoyoshi Akiba,Koji Iwano,Jun Ogata,Tetsuji Ogawa4,Nobutaka Ono,Takahiro Shinozaki,Koichi Shinoda,Hiroaki Nanjo,Hiromitsu Nishizaki,Masafumi Nishida,Ryuichi Nishimura,Sunao Hara,Takaaki Hori","New Speech Research Paradigm in the Cloud Era","情報処理学会研究報告","IPSJ SIG Technical Report",,"Vol. 2012-SLP-92","No. 4",,2012,July
"Masayoshi Yoshikawa,Takahiro Shinozaki,Koji Iwano,Sadaoi Furui","Multimodal speech recognition based on lightweight visual features",,"電子情報通信学会論文誌",,"Vol. J95-D","No. 3","pp. 618-627",2012,Mar.
"山畑 勇人,大久保 梨思子,山田 武志,今井 新悟,石塚 賢吉,Takahiro Shinozaki,西村 竜一,牧野 昭二,北脇 信彦","日本語スピーキングテストにおける文章読み上げ問題の採点に影響を及ぼす要因の検討","電子情報通信学会総合大会",,,,,,2012,Mar.
"Naoto Inose,Takahiro Shinozaki,Shiqiao Du,Sadaoki Furui,Masakazu Sekijima","A study on the potential energy minimization of proteins by Slice Chain Max-Sum algorithm","情報処理学会バイオ情報学研究会",,,"Vol. 2012-BIO-28","No. 20","pp. 1-8",2012,Mar.
"房福明,Takahiro Shinozaki,Yasuo Horiuchi,黒岩眞吾,SADAOKI FURUI,Toshimitsu Musha","Electrooculogram input based speech synthesis interface and user adaptation","第39回知能システムシンポジウム","第39回知能システムシンポジウム資料",,,,"pp. 293-298",2012,Mar.
"黒岩 眞吾,柘植 覚,張 文彬,Takahiro Shinozaki,Yasuo Horiuchi","AWA長期間収録音声コーパスと時期差の分析","日本音響学会","春季講演論文集",,,,"pp. 83-86.",2012,Mar.
"Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾","言語モデルの順向き最尤文選択適応への教師なしクロスバリデーション適応法の応用","日本音響学会","春季講演論文集",,,,"pp. 99-100.",2012,Mar.
"西村 洋介,今村 大輔,Yasuo Horiuchi,Kazuhiko Kawamoto,Takahiro Shinozaki,黒岩 眞吾","Kinectとパーティクルフィルタを用いたHMM手話認識手法の検討",,"信学技報",,"vol. 111","no. 431","pp. 161-166.",2012,Feb.
"栗原 理沙,石塚 賢吉,西村 竜一,Takahiro Shinozaki,山田 武志,今井 新悟","日本語発話能力測定ウェブシステムのための留学生発話分析",,"信学技報",,"vol. 111","no. 431","pp. 141-142.",2012,Feb.
"房福明,Takahiro Shinozaki,Yasuo Horiuchi,黒岩眞吾,SADAOKI FURUI,Toshimitsu Musha","隠れマルコフモデルを用いた眼電位認識の研究","電子情報通信学会音声研究会","信学技報",,,"No. SP2011-117","pp. 97-102",2012,Feb.
"N. Inose,T. Shinozaki,S. Du,S. Furui,M. Sekijima","Protein Potential Energy Minimization Using Slice Chain Max-Sum Algorithm","26th Annual Symposium of The Protein Society",,,,,,2012,
"Takahiro Shinozaki,Toshinao Iwaki,Shiqiao Du,Masakazu Sekijima,Sadaoki Furui","Distance-based factor graph linearization and sampled max-sum algorithm for efficient 3D potential decoding of macromolecules",,"IPSJ Transaction on Bioinformatics",,"Vol. 4",,"pp. 34-44",2011,Dec.
"張 文彬,陸 昊澤,Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾","時期差に頑健な話者識別手法","バイオメトリクスと認識・認証シンポジウム",,,,,,2011,Nov.
"Felipe Gomez-Caballero,Takahiro Shinozaki,Sadaoki Furui,Koichi Shinoda","Person Authentication using 3D Human Motion","ACM Multimedia'11","Proc. Joint ACM Workshop on Human Gesture and Behavior Understanding  2011 (J-HGBU '11)",,,,"pp. 35-40",2011,Nov.
"Takahiro Shinozaki,Sadaoki Furui","Strategies for model training and adaptation based on data dependency control","APSIPA ASC 2011","Proc. APSIPA ASC 2011 Xi’an",,,,,2011,Oct.
"Takahiro Shinozaki,Masakazu Sekijima,Shigeki Hagihara,Sadaoki Furui","Compact speech decoder based on pure functional programming","APSIPA ASC 2011","Proc. APSIPA ASC 2011",,,,,2011,Oct.
"Takahiro Shinozaki,Toshinao Iwaki,Shichao Du,Masakazu Sekijima,SADAOKI FURUI","Distance based Graph Linearization and Sampled Max-sum Algorithm for Efficient 3D Potential Decoding of Macromolecules","情報処理学会第26回バイオ情報学研究発表会","情報処理学会研究会報告",,,,"  2011-BIO-26",2011,Sept.
"紺野 遼輔,Takahiro Shinozaki,Yasuo Horiuchi,黒岩 眞吾","構内アナウンス環境下における音声認識のための音声区間検出","日本音響学会",,,,,"pp. 151-152.",2011,Sept.
"Takahiro Shinozaki,Yu Kubota,Sadaoki Furui,Eiji Utsunomiya,Yasutaka Shindoh","Sentence selection by direct likelihood maximization for language model adaptation","INTERSPEECH 2011","Proc. INTERSPEECH 2011",,,,"pp. 613-616",2011,Aug.
"Toshinao Iwaki,Takahiro Shinozaki,SADAOKI FURUI","Sampled Max-Sum Algorithm and Application to 3D Structure Prediction of Proteins","日本蛋白質科学会年会",,,,,,2011,June
"Takahiro Shinozaki,Masakazu Sekijima,Shigeki Hagihara,SADAOKI FURUI","純粋関数型言語を用いた超コンパクトデコーダの開発","情報処理学会",,,,,,2011,Apr.
"Takahiro Shinozaki,Masakazu Sekijima,Shigeki Hagihara,Sadaoki Furui","A compact speech decoder based on pure functional programming","IPSJ-SIGPRO","Manuscript for presentation at IPSJ-SIGPRO, 25 April 2011.",,,"  2010-5","  6",2011,Apr.
"Yu Kubota,Takahiro Shinozaki,SADAOKI FURUI,Eiji Utsunomiya,Yasutaka Shindo","N-gramカウントを用いた言語モデルの効率的な選択学習","日本音響学会2011年春季研究発表会","日本音響学会2011年春季講演論文集","日本音響学会",,"No. 3-5-2","pp. 73-74",2011,Mar.
"Kento Ozaki,Takahiro Shinozaki,Toshimitsu Musha,SADAOKI FURUI","眼電位を用いた音声合成インタフェースの研究","日本音響学会2011年春季研究発表会","日本音響学会2011年春季講演論文集","日本音響学会",,"No. 3-4-13","pp. 1621-1622",2011,Mar.
"張 ?,Oonishi Tasuku,Takahiro Shinozaki,SADAOKI FURUI","クロス言語検索を用いた中国語音声認識による乗換案内システム","日本音響学会2011年春季講演発表会","日本音響学会2011年春季講演論文集","日本音響学会",,"No. 2-5-7","pp. 61-62",2011,Mar.
"Hosana Kamiyama,Takahiro Shinozaki,Koji Iwano,Sadaoki Furui","An Efficient Prosody Adaptation Method and Its Application to HMM-based Speech Synthesis","APSIPA2010","Proc. of the Second APSIPA Annual Summit and Conference",,,,"pp. 82-85",2010,Dec.
"Toshiya Wada,Takahiro Shinozaki,Sadaoki Furui","Investigations of features and estimators for speech-based age estimation","APSIPA2010","Proc. of the Second APSIPA Annual Summit and Conference","APSIPA",,,"pp. 470-473",2010,Dec.
"Koichi Takagi,Ryoichi Kawada,Takahiro Shinozaki,Sadaoki Furui","Visualization of Audio Information for Home Video Highlight Extraction","APSIPA2010","Proc. of the Second APSIPA Annual Summit and Conference",,,,"pp. 145-148",2010,Dec.
"Takahiro Shinozaki,Yu Kubota,Sadaoki Furui","Unsupervised Acoustic Model Adaptation Based on Ensemble Methods",,"IEEE journal of Selected Topics in Signal Processing","IEEE","Vol. 4","No. 6","pp. 1007-1015",2010,Dec.
"高木 幸一,Ryoichi Kawata,Takahiro Shinozaki,SADAOKI FURUI","ホームビデオからのハイライト検出支援のための音声情報の視覚化","日本音響学会2010年秋季研究発表会","日本音響学会2010年秋季講演論文集","日本音響学会",,"No. 2-9-11","pp. 69-70",2010,Sept.
"Takahiro Shinozaki,Masakazu Sekijima,Shigeki Hagihara,SADAOKI FURUI","柔軟でコンパクトな純粋関数型デコーダの検討","日本音響学会2010年秋季研究発表会","日本音響学会2010年秋季講演論文集","日本音響学会",,"No. 1-Q-26","pp. 181-182",2010,Sept.
"Takahiro Shinozaki,Sadaoki Furui,Tatsuya Kawahara","Gaussian Mixture Optimization Based on Efficient Cross-Validation",,"IEEE Journal of Selected Topics in Signal Processing","IEEE","Vol. 4","No. 3","pp. 540-547",2010,June
"Toshiya Wada,Takahiro Shinozaki,SADAOKI FURUI","年齢推定のための音声特徴量および推定器の検討",,"電子情報通信学会 技術研究報告","社団法人 電子情報通信学会","Vol. SP2010-27",,"pp. 31-36",2010,June
"Felipe Gomez-Caballero,Takahiro Shinozaki,Sadaoki Furui","User identification using Time-of-Flight camera image streams",,"情報処理学会創立50周年記念(第72回)全国大会","情報処理学会",,"No. 5X-8","pp. 2-615?2-626",2010,Mar.
"Hosana Kamiyama,Takahiro Shinozaki,Koji Iwano,SADAOKI FURUI","自然性と個人性に優れた音声合成のための音素継続時間長適応法","日本音響学会2010年春季研究発表会","日本音響学会2010年春季講演論文集","日本音響学会",,"No. 2-7-1","pp. 329-330",2010,Mar.
"Yu Kubota,Takahiro Shinozaki,Sadaoki Furui","Investigations on Ensemble Based Unsupervised Adaptation Methods","ICASSP 2010","IEEE ICASSP2010","IEEE",,,"pp. 4874-4877",2010,Mar.
"Shunsuke Nishii,Takahiro Shinozaki,SADAOKI FURUI","日本語話し言葉コーパスを用いた異なるタスクに対する音声認識","日本音響学会2010年春季研究発表会","日本音響学会2010年春季講演論文集","日本音響学会",,"No. 1-6-10","pp. 27-28",2010,Mar.
"Takahiro Shinozaki,Yu Kubota,Paul Dixon,SADAOKI FURUI","識別学習モデルと教師なしCV適応を用いたCSJ講演音声認識","日本音響学会2010年春季講演論文集","日本音響学会2010年春季講演論文集","日本音響学会",,"No. 1-6-14","pp. 37-38",2010,Mar.
"Toshiya Wada,Takahiro Shinozaki,SADAOKI FURUI","MLLR変換行列を特徴量として用いた年齢推定","日本音響学会2010年春季研究発表会","日本音響学会2010年春季講演論文集","日本音響学会",,"No. 2-6-13","pp. 83-84",2010,Mar.
"Hosana Kamiyama,Takahiro Shinozaki,Koji Iwano,SADAOKI FURUI","HMM音声合成における自然性と個人性に優れた韻律モデル適応法の検討",,"情報処理学会研究会報告","情報処理学会","Vol. 2010-SLP-80","No. 12","pp. 1-6",2010,Feb.
"Takahiro Shinozaki,古井 貞煕","教師無しアンサンブル適応法の提案と音響モデル適応への応用","第１２回情報論的学習理論ワークショップ",,,,,"p. 097.",2009,Oct.
"Takahiro Shinozaki,Mari Ostendorf,Les Atlas","Characteristics of speaking style and implications for speech recognition",,"The Journal of the Acoustical Society of America",,"Vol. 126","No. 3","pp. 1500-1510",2009,Sept.
"Takahiro Shinozaki,Sadaoki Furui","Target Speech GMM-based Spectral Compensation for Noise Robust Speech Recognition","INTERSPEECH 2009 BRIGHTON","INTERSPEECH 2009 BRIGHTON","2009 ISCA,",,,"pp. 1255-1258",2009,Sept.
"Takahiro Shinozaki,SADAOKI FURUI","目的音GMM尤度基準スペクトル補正法の諸評価","日本音響学会秋季研究発表会","日本音響学会2009年秋季講演論文集","日本音響学会",,"No. 1-1-10","pp. 31-32",2009,Sept.
"Hosana Kamiyama,Takahiro Shinozaki,Koji Iwano,SADAOKI FURUI","自然性と個人性に優れたF0パターン適応法","日本音響学会秋季研究発表会","日本音響学会2009年秋季講演論文集","日本音響学会",,"No. 1-2-7","pp. 249-250",2009,Sept.
"Takahiro Shinozaki","音響モデルのアンサンブル学習",,,,,"No. 11.",,2009,July
"Yu Kubota,Takahiro Shinozaki,SADAOKI FURUI","教師なしクロスバリデーション適応法の諸条件における評価","IPSJ SIG","情報処理学会研究報告, IPSJ SIG Technical Report","情報処理学会","Vol. 2009-SLP-77","No. 7",,2009,July
"Hosana Kamiyama,Takahiro Shinozaki,Koji Iwano,SADAOKI FURUI","F0パターン生成モデルのための数量化?類の平均値置換による話者適応法の検討",,"IEICE Tachnical Report, SP2009-38","The Institute of elecronics, information and communication engineers",,,"pp. 87-92",2009,June
"Takahiro Shinozaki,Yu kubota,Sadaoki Furui","Unsupervised cross-validation adaptation algorithms for improved adaptation performance","ICASSP 2009","IEEE ICASSP 2009","IEEE",,,"pp. 4377-4380",2009,Apr.
"Takahiro Shinozaki,Yu Kubota,SADAOKI FURUI","高精度音声認識のための教師なしクロスバリデーション適応法の提案","日本音響学会 2009年 春季研究発表会","日本音響学会2009年春季講演論文集",,,"No. 1-5-10","pp. 27-28",2009,Mar.
"Takahiro Shinozaki,Yu Kubota,SADAOKI FURUI","教師なしクロスバリデーション適応によるタスク適応","日本音響学会 2009年 春季研究発表会","日本音響学会2009年春季講演論文集",,,"No. 1-5-11","pp. 29-30",2009,Mar.
"Tomohisa Kawasaki,Oonishi Tasuku,Takahiro Shinozaki,SADAOKI FURUI","音声による３次元直接操作インタフェース","インタラクション2009","インタラクション2009",,,,"p. 43-44",2009,Mar.
"Koichi Takagi,米山 暁夫,Takahiro Shinozaki,SADAOKI FURUI","携帯端末上でのプロキシ編集",,"IEICE Tachnical Report",,,"No. IE2009-02","pp. 7-12",2009,Feb.
"Takahiro Shinozaki,Yu Kubota,SADAOKI FURUI","高精度音声認識のための教師なしクロスバリデーションおよび集合適応法の提案",,"IPSJ SIG echnical Report","社団法人 情報処理学会",,"No. 75","page 1-6",2009,Feb.
"Tomohisa Kawasaki,Oonishi Tasuku,Koji Iwano,Takahiro Shinozaki,SADAOKI FURUI","Voice-based direct manipulation interface for mouse cursor control","日本音響学会秋季研究発表会","日本音響学会2008年秋季講演論文集","日本音響学会",,"No. 1-1-23","p. 55-56",2008,Sept.
"Takahiro SHINOZAKI,Sadaoki FURUI","Target Speech GMM-based Spectral Compensation Filter for Noisy Speech Recognition","日本音響学会秋季研究発表会","日本音響学会2008年秋季講演論文集","日本音響学会",,"No. 1-1-1","p. 1-2",2008,Sept.
"Takahiro Shinozaki,Sadaoki Furui,Tatsuya Kawahara","Aggregated Cross-validation and Its Efficient Application to Gaussian Mixture Optimization","Interspeech2008","Interspeech2008",,,,"pp. 2382-2385",2008,Sept.
"Takahiro Shinozaki,Mari Ostendorf","Cross-validation and aggregated EM training for robust parameter estimation",,"Computer speech and language",,"Vol. 22","No. 2","pp. 185-195",2008,Aug.