Publications (in English)

Invited talk

• Takahiro Shinozaki, "Automated Development of Deep Neural Network Systems Based on Evolutionary Algorithms," SNL-2019, 2019.7
• Takahiro Shinozaki and Sadaoki Furui, "Strategies for Model Training and Adaptation Based on Data Dependency Control," APSIPA Overview, 2011.10

Journals

• 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, 2023-2
• 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, pp.1-13, 2022-7
• 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, 2021-12.
• Longfei Yang, Kaiqi Fu, Jinsong Zhang, Takahiro Shinozaki, "Non-native acoustic modeling for mispronunciation verification based on language adversarial representation learning," Neural Networks, 2021-7.
• Takahiro Shinozaki, Shinji Watanabe, Kevin Duh, "Automated Development of DNN Based Spoken Language Systems Using Evolutionary Algorithms," Book Chapter in Nasimul Noman, Hitoshi Iba, "Deep Neural Evolution - Deep Learning with Evolutionary Computation," Springer, 2020.
• Takafumi Moriya, Tomohiro Tanaka, Takahiro Shinozaki, Shinji Watanabe, Kevin Duh, "Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition," IEEE Transactions on Audio, Speech and Language Processing, Vol.27, No.1, pp77-88, 2019-1.
• Fuming Fang, Takahiro Shinozaki, "Electrooculography-based continuous eye-writing recognition system for efficient assistive communication systems," PLOS ONE 13(2):e0192684, 2018.
• 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, vol. 2016, Article ID 6898031, 9 pages, 2016.
• Felipe Gomez Caballero, Takahiro Shinozaki, Sadaoki Furui and Koichi Shinoda, "A Statistical Approach For Person Verification Using Human Behavioral Patterns," EURASIP Journal on Image and Video Processing, 2013:44, pp. 1-11, 2013-8.
• Takahiro Shinozaki, Toshinao Iwaki, Shiqiao Du, Masakazu Sekijima and 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, 2011.12
• Takahiro Shinozaki,Yu Kubota and Sadaoki Furui, "Unsupervised Acoustic Model Adaptation Based on Ensemble Methods," IEEE Journal of Selected Topics in Signal Processing, Vol. 4, No. 6, pp. 1007-1015, 2010.12
• Takahiro Shinozaki, Sadaoki Furui and Tatsuya Kawahara, "Gaussian Mixture Optimization Based on Efficient Cross-validation," IEEE Journal of Selected Topics in Signal Processing, Vol. 4, No. 3, pp. 540-547, 2010.6
• Takahiro Shinozaki, Mari Ostendorf and Les Atlas, "Characteristics of Speaking Style and Implications for Speech Recognition," The Journal of the Acoustical Society of America, Vol. 126, Issue 3, pp. 1500-1510, 2009.9
• Takahiro Shinozaki, and Mari Ostendorf, "Cross-validation and Aggregated EM Training for Robust Parameter Estimation," Computer Speech and Language, Vol.22/2, pp. 185-195, 2008.4
• Nelson Morgan, Qifeng Zhu, Andreas Stolcke, Kemal Sonmez, Sunil Sivadas, Takahiro Shinozaki, Mari Ostendorf, Pratibha Jain, Hynek Hermansky, Dan Ellis, George Doddington, Barry Chen, Ozgur Cetin, Herve Bourlard, and Marios Athineos, "Pushing the Envelope-aside," IEEE Signal Processing Magazine, Vol. 22, No.5, pp.81-88, 2005.9
• Takahiro Shinozaki and Sadaoki Furui, "Dynamic Bayesian Network-based Acoustic Models Incorporating Speaking Rate Effects," Trans of the IEICE, Vol.E87-D, No.10, pp.2339-2347, 2004.10
• Yoshinori Takei, Toshiya Ito and Takahiro Shinozaki, "Constructing an Optimal Family of Min-Wise Independent Permutations," Trans of the IEICE, Vol.E83-A, No.4, pp.747-755, 2000.4

Conferences

• Tingyuan Zhu, Shudong Liu, Yidong Wang, Derek F. Wong, Han Yu, Takahiro Shinozaki, Jindong Wang, "Learning from "Silly" Questions Improves Large Language Models, But Only Slightly," AAAI Workshop, 2025.2 (accepted)
• Ryota Komatsu, Takahiro Shinozaki, "Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT," Spoken Language Technology, 2024.11 (accepted)
• Zehua Zhou, Haoyuan Yang, Takahiro Shinozaki, "Self-Supervised Speaker Verification With Adaptive Threshold and Hierarchical Training," ICASSP 2024, pp. 12141-12145, 2024-4.
• Yu Iwamoto, Takahiro Shinozaki, "Memory Network-Based End-To-End Neural ES-KMeans for Improved Word Segmentation," INTERSPEECH 2023, pp. 486-490, 2023-8.
• Ryota Komatsu, Yusuke Kimura, Takuma Okamoto, Takahiro Shinozaki, "Continuous Action Space-based Spoken Language Acquisition Agent Using Residual Sentence Embedding and Transformer Decoder," ICASSP, 2023-6.
• 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," ICLR 2023, 2023-5.
• Yidong Wang, Bowen Zhang, Wenxin Hou, Zhen Wu, Jindong Wang, Takahiro Shinozaki, "Margin Calibration for Long-Tailed Visual Recognition," ACML2022, 2022-12.
• 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, 2022-11.
• Mingxin Zhang, Takahiro Shinozaki, "DNN-Rule Hybrid Dyna-Q for Sample-Efficient Task-Oriented Dialog Policy Learning," APSIPA2022, pp.1431-1437, 2022-11.
• 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, 2022-10.
• 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, 2022-9.
• Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Takahiro Shinozaki, "Streaming Target-Speaker ASR with Neural Transducer," INTERSPEECH 2022, pp. 2673-2677, 2022-9.
• 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, 2022-9.
• 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, 2022-9.
• 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, 2022-9.
• 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, 2022-7.
• 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," ICASSP 2022, pp.8282-8286, 2022-5.
• Tomohiro Tanaka, Ryota Komatsu, Takuma Okamoto, Takahiro Shinozaki, "Pronunciation Adaptive Self Speaking Agent Using WaveGrad," AAAI-SAS 2022, 8 pages, 2022-2.
• Xingrui Wang, Bowen Zhang, Takahiro Shinozaki, "Low-resource Mandarin Prosodic Structure Prediction Using Self-training," APSIPA2021, Paper ID 1564, pp. 859-862, 2021-12.
• Yu Iwamoto, Takahiro Shinozaki, "Unsupervised Spoken Term Discovery Using wav2vec 2.0," APSIPA2021, Paper ID 1554, pp. 1082-1086, 2021-12.
• 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, 2021-12.
• 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, pp37-42, 2021-11.
• Wenxin Hou, Jindong Wang, Xu Tan, Tao Qin, Takahiro Shinozaki, "Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching," Interspeech, pp3425-3429, 2021-9.
• Wenxin Hou, Yidong Wang, Shengzhou Gao, Takahiro Shinozaki, "Efficient Cross-Lingual Adaptation With Meta-Learning," IEEE ICASSP, pp.7028-7032, 2021-6.
• Hayato Shibata, Mingxin Zhang, Takahiro Shinozaki, "Unsupervised Acoustic-To-Articulatory Inversion Neural Network Learning Based on Deterministic Policy Gradient," IEEE Spoken Language Technology, pp.530-537, 2021-1.
• Tomohiro Tanaka, Takahiro Shinozaki, "Unsupervised Sound Source Localization From Audio-Image Pairs Using Input Gradient Map," ICPR 2021-1.
• 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," Proc. Interspeech, pp. 1037-1041, 2020-10.
• Mingxin Zhang, Tomohiro Tanaka, Wenxin Hou, Shengzhou Gao, Takahiro Shinozaki, "Sound-Image Grounding Based Focusing Mechanism for Efficient Automatic Spoken Language Acquisition," Proc. Interspeech, pp. 1436-1440, 2020-10.
• Longfei Yang, Kaiqi Fu, Jinsong Zhang, Takahiro Shinozaki, "Pronunciation Erroneous Tendency Detection with Language Adversarial Represent Learning," Proc. Interspeech, pp. 3042-3046, 2020-10.
• Jianshu Zhao, Shengzhou Gao, Takahiro Shinozaki, "Time-Domain Target-Speaker Speech Separation With Waveform-Based Speaker Embedding," Proc. Interspeech, pp. 4183-4187, 2020-10.
• Kent Hino, Yusuke Kimura, Yue Dong and Takahiro Shinozaki, "Dual Inheritance Evolution Strategy for Deep Neural Network Optimization," Proc. IEEE Congress on Evolution Computation (CEC), 7 pages, 2020-7.
• Shengzhou Gao, Wenxin Hou, Tomohiro Tanaka, Takahiro Shinozaki, "Spoken Language Acquisition Based on Reinforcement Learning and Word Unit Segmentation," Proc. ICASSP2020, pp.6144-6148, 2020-5. slides
• Tomohiro Tanaka, Takahiro Shinozaki, "Efficient free keyword detection based on cnn and end-to-end continuous dp-matching," Proc. ASRU, Paper ID SDR.6, pp.637-644, 2019-12.
• Yi Liu, Bairong Zhuang, Zhiyu Li, Takahiro Shinozaki, "Cross-Domain Speaker Recognition using Cycle-Consistent Adversarial Networks," Proc. APSIPA, Paper ID 235, pp.2070-2074, 2019-11.
• Xu Han, Takahiro Shinozaki, Ryota Kobayashi, "Effective and Stable Neuron Model Optimization Based on Aggregated CMA-ES," Proc. ICASSP, pp.1264-1268, 2019-5.
• Bairong Zhuang, Wenbo Wang, Takahiro Shinozaki, "Investigation of Attention-Based Multimodal Fusion and Maximum Mutual Information Objective for DSTC7 Track3," Proc. DSTC7, 2019-1.
• Yilong Peng, Hayato Shibata, Takahiro Shinozaki, "Reward Only Training of Encoder-Decoder Digit Recognition Systems Based on Policy Gradient Methods," Proc. APSIPA, pp.1934-1939, 2018-11.
• Tomohiro Tanaka, Takahiro Shinozaki, "F-Measure Based End-To-End Optimization of Neural Network Keyword Detectors," Proc. APSIPA, pp.1456-1461, 2018-11.
• 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), pp. 130-135, 1027, 2018-5.
• Taku Kato, Takahiro Shinozaki, "Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection," Proc. IEEE ICASSP, pp.5759-5763, 2018-4. arxiv
• Hayato Shibata, Taku Kato, Takahiro Shinozaki, Shinji Watanabe, "Composite Embedding Systems for Zerospeech2017 Track1," Proc. IEEE ASRU 2017, pp. 747-753, 2017-12.
• Hao Qin, Takahiro Shinozaki, Kevin Duh, "Evolution Strategy Based Automatic Tuning of Neural Machine Translation Systems," Proc. International Workshop on Spoken Language Translation (IWSLT) 2017, pp.120-128, 2017-12.
• 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), 2017-12, Long Beach, USA.
• Takahiro Shinozaki, Shinji Watanabe, Daichi Mochihashi, Graham Neubig, "Semi-Supervised Learning of a Pronunciation Dictionary from Disjoint Phonemic Transcripts and Text," Proc. Interspeech 2017, pp. 2546-2550, 2017-8, Stockholm, Sweden.
• 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-IS13-03, 2017-8.
• 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-IS13-06, 2017-8.
• Tomohiro Tanaka, Takahiro Shinozaki, Shinji Watanabe, Takaaki Hori, "Evolution Strategy Based Neural Network Optimization and LSTM Language Model for Robust Speech Recognition," Proceedings of the 4th International Workshop on Speech Processing in Everyday Environments CHiME 2016-9, pp.32-35, 2016-9.
• Tomohiro Tanaka, Takafumi Moriya, Takahiro Shinozaki, Shinji Watanabe, Takaaki Hori, Kevin Duh, "Automated Structure Discovery and Parameter Tuning of Neural Network Language Model based on Evolution Strategy", Proc. Spoken Language Technology (SLT), pp. 665-671, 2016-12.
• Takuya Yoshioka, Katsunori Ohnishi, Fuming Fang, Tomohiro Nakatani, "Noise robust speech recognition using recent developments in neural networks for computer vision," ICASSP, pp.5730-5734, 2016-3.
• Takafumi Moriya, Tomohiro Tanaka, Takahiro Shinozaki, Shinji Watanabe, and Kevin Duh, "Automation of System Building for State-of-the-art Large Vocabulary Speech Recognition Using Evolution Strategy," Proc. IEEE 2015 Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 610-616, 2015.
• Takahiro Shinozaki, Shinji Watanabe, "Structure discovery of deep neural network based on evolutionary algorithms," Proc. ICASSP, 2015.4.
• Fuming Fang, Takahiro Shinozaki, Takao Kobayashi, "An automatic input protocol recommendation method for tailored switch-to-speech communication aid systems," Proc. 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2014, PID:1184, Seim Reap, Cambodia, 2014.12
• Felipe Gomez-Caballero, Takahiro Shinozaki, Sadaoki Furui and Koichi Shinoda, "Statistical Person Verification Using Behavioral Patterns from Complex Human Motion," Proc. ICIAP Social Behaviour Analysis workshop, pp. 550-558, 2013.9.
• Takaaki Ishii, Hiroki Komiyama, Takahiro Shinozaki, Yasuo Horiuchi and Shingo Kuroiwa, Reverberant Speech Recognition Based on Denoising Autoencoder, Proc. Interspeech 2013, pp. 3512-3516, 2013.8.
• Takahiro Shinozaki, Sadaoki Furui, Yasuo Horiuchi and Shingo Kuroiwa "Pipeline Decomposition of Speech Decoders and Their Implementation Based on Delayed Evaluation," Proc. APSIPA, 2012.12.
• Yutaka Ono, Misuzu Otake, Takahiro Shinozaki, Ryuichi Nisimura, Takeshi Yamada, Kenkichi Ishizuka, Yasuo Horiuchi, Shingo Kuroiwa and Shingo Imai "Open Answer Scoring for S-CAT Automated Speaking Test System Using Support Vector Regression," Proc. APSIPA, 2012.12.
• Fuming Fang, Takahiro Shinozaki, Yasuo Horiuchi, Shingo Kuroiwa, Sadaoki Furui, Toshimitsu Musha "HMM Based Continuous EOG Recognition for Eye-input Speech Interface," Proc. Interspeech 2012.9.
• Haoze Lu,Wenbin Zhang,Yasuo Horiuchi, Takahiro Shinozaki and Shingo Kuroiwa, "PCA Transformation Based Inter-session Variability Suppression for Text-Independent Speaker Identification," Proc 8th Conference on Natural Language Processing and Knowledge Engineering (NLPKE2012), Hefei,China, pp.463-473, 2012.9
• N. Inose, T. Shinozaki, S. Du, S. Furui and M. Sekijima "Protein Potential Energy Minimization Using Slice Chain Max-Sum Algorithm," The 26th Annual Symposium of The Protein Society, poster. 2012.8.
• Takahiro Shinozaki, Yasuo Horiuchi, Shingo Kuroiwa, "Unsupervised CV language model adaptation based on direct likelihood maximization sentence selection", Proc. ICASSP 2012, pp. 5029-5032, 2012.3.
• Shiori Takenaka, Takahiro Shinozaki, Yasuo Horiuchi, Shingo Kuroiwa, "Pseudo speaker models for text-independent speaker verification using rank threshold," 7th IEEE Conference on Natural Language Processing and Knowledge Engineering, pp. 265-268, 2011.11.
• Felipe Gomez-Caballero, Takahiro Shinozaki, Sadaoki Furui, and Koichi Shinoda, "Person authentication using 3D human motion," Proc. J-HGBU'11 ACM Multimedia joint workshop, pp. 35-40, 2011.11.
• Takahiro Shinozaki, Masakazu Sekijima, Shigeki Hagihara, and Sadaoki Furui, "A Compact Speech Decoder Based on Pure Functional Programming," Proc. APSIPA, CDROM proceedings, 2011.10.
• Takahiro Shinozaki, Yu Kubota, Sadaoki Furui, Eiji Utsunomiya, and Yasutaka Shindoh, "Sentence Selection by Direct Likelihood Maximization for Language Model Adaptation," Proc. Interspeech, pp. 613-616, 2011.9.
• Hosana Kamiyama, Takahiro Shinozaki, Koji Iwano, and Sadaoki Furui, "An Efficient Prosody Adaptation Method and Its Application to HMM-based Speech Synthesis," Proc. APSIPA, pp.82-85, 2010.12.
• Toshiya Wada, Takahiro Shinozaki, and Sadaoki Furui "Investigations of Features and Estimators for Speech-based Age Estimation," Proc. APSIPA, pp.470-473, 2010.12.
• Koichi Takagi, Ryoichi Kawada, Takahiro Shinozaki, and Sadaoki Furui, "Hightlight Extraction from a Home Vide Considering Audiovisual Relationship," Proc. APSIPA, pp.145-148, 2010.12
• Yu Kubota, Takahiro Shinozaki, and Sadaoki Furui, "Investigations on Ensemble Based Unsupervised Adaptation Methods," Proc. ICASSP, pp. 4874-4877, 2010.3
• Takahiro Shinozaki and Sadaoki Furui, "Target Speech GMM-based Spectral Compensation for Noise Robust Speech Recognition," Proc. INTERSPEECH, pp. 1255-1258, 2009.9
• Takahiro Shinozaki, Yu Kubota, and Sadaoki Furui, "Unsupervised Cross-validation Adaptation Algorithms for Improved Adaptation Performance," Proc. ICASSP, pp. 4377-4380, 2009.4
• Takahiro Shinozaki, Sadaoki Furui, and Tatsuya Kawahara, "Aggregated Cross-validation and Its Efficient Application to Gaussian Mixture Optimization," Proc. Interspeech, pp. 2382-2385, 2008.9
• Takahiro Shinozaki and Tatsuya Kawahara, "GMM and HMM Training by Aggregated EM Algorithm with Increased Ensemble Sizes for Robust Parameter Estimation," Proc. ICASSP, pp. 4405-4408, 2008.4
• Takahiro Shinozaki and Tatsuya Kawahara, "HMM Training Based on CV-EM and CV Gaussian Mixture Optimization," Proc. ASRU 2007, pp. 318-322, 2007.12
• Takahiro Shinozaki, and Tatsuya Kawahara, "Gaussian Mixture Optimization for HMM Based on Efficient Cross-validation," Proc. Interspeech, pp. 2061-2064, 2007.8
• Takahiro Shinozaki and Mari Ostendorf, "Cross-validation EM Training for Robust Parameter Estimation," Proc. ICASSP, pp. 437-440, 2007.4
• Xavier Anguera Miro, Takahiro Shinozaki, Chuck Wooters, and Javier Hernando, "Model Complexity Selection and Cross-validation EM Training for Robust Speaker Diarization," Proc. ICASSP, pp. 273-276, 2007.4
• Mei-Yuh Hwang, Xin Lei, Wen Wang, and Takahiro Shinozaki, "Investigation on Mandarin Broadcast News Speech Recognition," Proc. ICSLP, pp1233-1236, 2006.9
• Takahiro Shinozaki, "HMM State Clustering Based on Efficient Cross-Validation," Proc. ICASSP, pp.1157-1160, 2006.5
• Takahiro Shinozaki and Mari Ostendorf, "A Cross-Likelihood Validation of the EM Algorithm for Robust Parameter Training," GALE PI Meeting, Boston, 2006.3
• Takahiro Shinozaki, Mari Ostendorf, and Les Atlas, "Data Sampling for Improved Speech Recognizer Training," Proc. EUROSPEECH, pp.1693-1696, 2005.9
• Sadaoki Furui, Tomohisa Ichiba, Takahiro Shinozaki, Edward W.D. Whittaker, and Koji Iwano, "Cluster-based Modeling for Ubiquitous Speech Recognition," Proc. EUROSPEECH, pp. 2865-2868, 2005.9
• B. Chen, O. Cetin, G. Doddington, N. Morgan, M. Ostendorf, T. Shinozaki, and Q. Zhu, "A CTS Task for Meaningful Fast-turnaround Experiments," Proc. Rich Transcription 2004, Palisades, NY, 2004.11
• Takahiro Shinozaki and Sadaoki Furui, "Spontaneous Speech Recognition Using a Massively Parallel Decoder," Proc. ICSLP, pp. 1705-1708, 2004.10
• Takahiro Shinozaki and Sadaoki Furui, "Hidden Mode HMM using Bayesian Network for Modeling Speaking Rate Fluctuation," Proc. ASRU, pp.417-422, 2003.12
• Takahiro Shinozaki and Sadaoki Furui, "Time Adjustable Mixture Weights for Speaking Rate Fluctuation," Proc. EUROSPEECH, Vol.2, pp. 973-976, 2003.9
• Takahiro Shinozaki and Sadaoki Furui, "An Assessment of Automatic Recognition Techniques for Spontaneous Speech in Comparison With Human Performance," Proc. Spontaneous Speech Processing and Recognition, pp. 95-98, 2003.4
• Tadasuke Yokoyama, Takahiro Shinozaki, Koji Iwano, Sadaoki Furui, "Unsupervised Class-based Language Model Adaptation for Spontaneous Speech Recognition," Proc ICASSP, Hong Kong, Vol. 1, pp. 236-239, 2003.4
• Tatsuya Kawahara, Hiroaki Nanjo, Takahiro Shinozaki and Sadaoki Furui, "Benchmark Test for Speech Recognition Using the Corpus of Spontaneous Japanese," Proc. SSPR, Tokyo, pp.135-138, 2003.4
• Tadasuke Yokoyama, Takahiro Shinozaki, Koji Iwano and Sadaoki Furui, "Unsupervised Language Model Adaptation Using Word Classes for Spontaneous Speech Recognition," Proc. SSPR, Japan, pp.71-74, 2003.4
• Takahiro Shinozaki and Sadaoki Furui, "A New Lexicon Optimization Method for LVCSR Based on Linguistic and Acoustic Characteristics of Words," Proc. ICSLP, Denver, vol.1, pp.717-720, 2002.9
• Takahiro Shinozaki and Sadaoki Furui, "Analysis on Individual Differences in Automatic Transcription of Spontaneous Presentations," Proc. ICASSP, Orlando, vol.1, pp.729-732, 2002.5
• Takahiro Shinozaki and Sadaoki Furui, "Error Analysis Using Decision Trees in Spontaneous Presentation Speech Recognition," Proc. ASRU, Trento, 2001.12
• Takahiro Shinozaki, Chiori Hori and Sadaoki Furui, "Towards Automatic Transcription of Spontaneous Presentations," Proc. EUROSPEECH, Denmark, vol.1, pp.491-494, 2001.9
• Sadaoki Furui, Koji Iwano, Chiori Hori, Takahiro Shinozaki, Yohei Saito and Satoshi Tamura, "Ubiquitous Speech Processing," Proc. ICASSP, Salt Lake City, vol.1, pp.13-16, 2001.5
• Sadaoki Furui, Kikuo Maekawa, Hitoshi Isahara, Takahiro Shinozaki and Takashi Ohdaira, "Toward the Realization of Spontaneous Speech Recognition ---Introduction of a Japanese Priority Program and Preliminary Results," Proc. ICSLP. Beijing, Vol.3, pp.518-521, 2000.10

etc.

• Yoshitaka Nishimura, Takahiro Shinozaki, Koji Iwano, and Sadaoki Furui "Noise-robust speech recognition using multi-band spectral features," (The 148th Meeting of the Acoustical Society of America, 2004.10).