Furui, Sadaoki - Department of Computer Science, Tokyo Institute of Technology

• Language Model Adaptation for Resource Deficient Languages Using Translated Data
• A Unified Approach to Japanese and English Question Answering Edward Whittaker Julien Hamonic Sadaoki Furui
• SENTENCE EXTRACTION-BASED PRESENTATION SUMMARIZATION TECHNIQUES AND EVALUATION METRICS
• UNSUPERVISED LANGUAGE MODEL ADAPTATION USING WORD CLASSES FOR SPONTANEOUS SPEECH RECOGNITION
• AUTOMATIC SENTENCE SEGMENTATION OF SPEECH FOR AUTOMATIC SUMMARIZATION
• UNSUPERVISED CROSS-VALIDATION ADAPTATION ALGORITHMS FOR IMPROVED ADAPTATION PERFORMANCE
• TWO-STAGE AUTOMATIC SPEECH SUMMARIZATION BY SENTENCE EXTRACTION AND COMPACTION
• FINITE-STATE TRANSDUCER BASED HUNGARIAN LVCSR WITH EXPLICIT MODELING OF PHONOLOGICAL CHANGES
• INVESTIGATIONS ON ENSEMBLE BASED UNSUPERVISED ADAPTATION METHODS Yu Kubota, Takahiro Shinozaki, Sadaoki Furui
• DEVELOPMENT OF A SPEECH RECOGNITION SYSTEM FOR ICELANDIC USING MACHINE TRANSLATED TEXT
• Statistical Modeling for Spontaneous Speech Recognition
• CSJ lecture speech recognition based on a discriminatively trained acoustic model and CV adaptation. by Takahiro Shinozaki, Yu Kubota, Paul Dixon, and Sadaoki Furui (Tokyo Institute of Technology)
• A study on robust audiovisual speech recognition
• AUTOMATIC SPEECH SUMMARIZATION APPLIED TO ENGLISH BROADCAST NEWS SPEECH
• Robust Methods in Automatic Speech Recognition and Understanding Sadaoki Furui
• Inference Network-based Indonesian Spoken Query Information Retrieval
• Time Adjustable Mixture Weights for Speaking Rate Fluctuation Takahiro Shinozaki, Sadaoki Furui
• ( ) Voice Activity Detection(VAD)
• Introduction of the 21st Century COE Program "Framework for Systematization and Application of Large-scale Knowledge Resources"
• SPEECH RECOGNITION TECHNOLOGY IN THE UBIQUITOUS/WEARABLE COMPUTING ENVIRONMENT
• 17 (2011 3 ) Copyright(C) 2011 The Association for Natural Language Processing.
• Development of a WFST based Speech Recognition System for a Resource Deficient Language Using
• AN ASSESSMENT OF AUTOMATIC RECOGNITION TECHNIQUES FOR SPONTANEOUS SPEECH IN COMPARISON WITH HUMAN PERFORMANCE
• Audio-Visual Person Authentication Using Speech and Ear Images Koji Iwano, Tomoharu Hirose, Eigo Kamibayashi, and Sadaoki Furui
• Dain Kaplan {dain,ryu-i,take}@cl.cs.titech.ac.jp
• SPEAKER ADAPTABLE MULTILINGUAL SYNTHESIS Javier Latorre, Koji Iwano, Sadaoki Furui
• Faculty Advisors Faculty Advisors are assigned
• Cross-language Synthesis with a Polyglot Synthesizer Javier Latorre, Koji Iwano, Sadaoki Furui
• STEPS TOWARD FLEXIBLE SPEECH RECOGNITION RECENT PROGRESS AT TOKYO INSTITUTE OF TECHNOLOGY
• NOISE ADAPTATION OF HMMS USING NEURAL NETWORKS Sadaoki Furui and Daisuke Itoh
• ON-LINE INCREMENTAL SPEAKER ADAPTATION WITH AUTOMATIC SPEAKER CHANGE DETECTION
• Belief-Based Nonlinear Rescoring in Thai Speech Understanding Chai Wutiwiwatchai and Sadaoki Furui
• BIMODAL SPEECH RECOGNITION USING LIP MOVEMENT MEASURED BY OPTICALFLOW ANALYSIS
• Selected topics from 40 years of research on speech and speaker recognition Sadaoki Furui 1
• A Study on Speaker-Adaptable Multilingual Synthesis
• A LANGUAGE MODELING APPROACH TO QUESTION ANSWERING ON SPEECH TRANSCRIPTS
• THE TITECH LARGE VOCABULARY WFST SPEECH RECOGNITION SYSTEM Paul R. Dixon1
• QUESTION ANSWERING AS A CLASSIFICATION TASK Edward Whittaker and Sadaoki Furui
• UBIQUITOUS SPEECH PROCESSING Sadaoki Furui, Koji Iwano, Chiori Hori, Takahiro Shinozaki, Yohei Saito, and Satoshi Tamura
• Generalization problem in ASR acoustic model training and adaptation
• A JAPANESE NATIONAL PROJECT ON SPONTANEOUS SPEECH CORPUS AND PROCESSING TECHNOLOGY
• COMBINING GAUSSIAN MIXTURE MODEL WITH GLOBAL VARIANCE TERM TO IMPROVE THE QUALITY OF AN HMM-BASED POLYGLOT SPEECH SYNTHESIZER
• HIDDEN MODE HMM USING BAYESIAN NETWORK FOR MODELING SPEAKING RATE FLUCTUATION
• 540 IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, VOL. 4, NO. 3, JUNE 2010 Gaussian Mixture Optimization Based
• FHMM for Robust Speech Recognition in Home Environment Agnieszka Betkowska, Koichi Shinoda, and Sadaoki Furui
• Audio-Visual Speech Recognition Using New Lip Features Extracted from Side-Face Images
• A ROBUST MULTI-MODAL SPEECH RECOGNITION METHOD USING OPTICAL-FLOW ANALYSIS
• Audio-Visual Speech Recognition Using Lip Movement Extracted from Side-Face Images
• Initial Evaluation of the .NET Framework as a Platform for Speech Recognition Paul R. Dixon Sadaoki Furui
• IPSJ SIG Technical Report A Prosody Adaptation Method for
• CSJ : (CSJ) 189.47 43.11
• Development of a flexible and compact pure functional decoder. by SHINOZAKI Takahiro, SEKIJIMA Masakazu, HAGIHARA Shigeki and SADAOKI Furui (Tokyo Institute of Technology)
• CONFIDENCE SCORING FOR ANN-BASED SPOKEN LANGUAGE UNDERSTANDING
• Predicting the phonetic realizations of word-final consonants in context A challenge for French grapheme-to-phoneme converters
• MDL-Based Cluster Number Decision Methods for Speaker Clustering and MLLR Adaptation Zhipeng Zhang and Sadaoki Furui
• Language model topic and style adaptation for Thai broadcast news ASR * Markpong Jongtaveesataporn, Sadaoki Furui
• EVALUATION OF TREE-STRUCTURED PIECEWISE-LINEAR-TRANSFORMATION-BASED NOISE ADAPTATION
• TOWARD THE REALIZATION OF SPONTANEOUS SPEECH RECOGNITION
• SPEECH MODELING BASED ON COMMITTEE-BASED ACTIVE LEARNING Yuzo Hamanaka
• TOWARD SUMMARIZATION OF BROADCAST NEWS SPEECH
• STEPS TOWARD NATURAL HUMAN-MACHINE COMMUNICATION IN THE 21ST
• IMPROVEMENTS IN AUTOMATIC SPEECH SUMMARIZATION AND EVALUATION METHODS
• ROBUST SPEECH RECOGNITION VIA MODELING SPECTRAL COEFFICIENTS WITH HMM'S WITH COMPLEX GAUSSIAN
• PIECEWISE-LINEAR TRANSFORMATION-BASED HMM ADAPTATION FOR NOISY SPEECH
• Automatic Summarization of English Broadcast News Speech
• SPEECH-RATE-VARIABLE HMM-BASED JAPANESE TTS SYSTEM Koji Iwano, Masahiro Yamada, Taro Togawa, and Sadaoki Furui
• A Study on Increasing Robustness against Speaker and Noise Variations in Speech Recognition
• NOISE ROBUST SPEECH RECOGNITION USING PROSODIC INFORMATION K. Iwano, T. Seki, and S. Furui
• AUTOMATIC SPEECH SUMMARIZATION BASED ON SENTENCE EXTRACTION AND Tomonori Kikuchi, Sadaoki Furui
• DERIVING DISAMBIGUOUS QUERIES IN A SPOKEN INTERACTIVE ODQA SYSTEM Chiori Hori, Takaaki Hori, Hideki Isozaki,
• Recent Advances in Spontaneous Speech Recognition and Understanding Sadaoki Furui
• Predictive Hidden Markov Model Selection for Decision Tree State Tying Jen-Tzung Chien a
• Combination of Finite State Automata and Neural Network for Spoken Language Understanding
• Evaluation Method for Automatic Speech Summarization Chiori Hori and Takaaki Hori
• IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, VOL. 12, NO. 4, JULY 2004 401 Speech-to-Text and Speech-to-Speech Summarization
• Overview of the 21st Century COE Program "Framework for Systematization and Application of Large-scale Knowledge Resources"
• IMPROVEMENT OF AUDIO-VISUAL SPEECH RECOGNITION IN CARS Satoshi Tamura, Koji Iwano and Sadaoki Furui
• Language Models and Dialogue Strategy for a Voice QA System Daewoo Kim, Sadaoki Furui, Hideki Isozaki
• A STREAM-WEIGHT OPTIMIZATION METHOD FOR AUDIO-VISUAL SPEECH RECOGNITION USING MULTI-STREAM HMMS
• Noise-Robust Speaker Verification Using F0 Features Koji Iwano, Taichi Asami, and Sadaoki Furui
• Spontaneous Speech Recognition Using a Massively Parallel Decoder Takahiro Shinozaki
• Unsupervised Language Model Adaptation Methods for Spontaneous Speech Luc Lussier, Edward W.D. Whittaker, Sadaoki Furui
• POLYGLOT SYNTHESIS USING A MIXTURE OF MONOLINGUAL Javier Latorre, Koji Iwano, Sadaoki Furui
• SPONTANEOUS SPEECH RECOGNITION AND SUMMARIZATION
• Stream-Weight Optimization by LDA and Adaboost for Multi-Stream Speaker Verification
• Analysis of Spectral Space Reduction in Spontaneous Speech and Its Effects on Speech Recognition Performances
• ROBUST HIGHLIGHT EXTRACTION USING MULTI-STREAM HIDDEN MARKOV MODELS FOR BASEBALL VIDEO
• A Statistical Classification Approach to Question Answering using Web Data Edward Whittaker Sadaoki Furui
• TREC2005 Question Answering Experiments at Tokyo Institute of Technology Edward Whittaker Pierre Chatain Sadaoki Furui
• 21st Century COE Program "Framework for Systematization and Application of Large-scale Knowledge Resources"
• SENTENCE EXTRACTION-BASED AUTOMATIC SPEECH SUMMARIZATION AND EVALUATION TECHNIQUES
• SCENE RECOGNITION USING HIDDEN MARKOV MODELS FOR VIDEO DATABASE Koichi Shinoda, Nguyen Huu Bach, Sadaoki Furui,
• TOWARD ROBUST MULTIMODAL SPEECH RECOGNITION Satoshi Tamura, Koji Iwano and Sadaoki Furui
• New approach to polyglot synthesis: how to speak any language with anyone's voice
• A STREAM-WEIGHT AND THRESHOLD ESTIMATION METHOD USING ADABOOST FOR MULTI-STREAM SPEAKER VERIFICATION
• TOPIC AND STYLISTIC ADAPTATION FOR SPEECH SUMMARISATION Pierre Chatain, Edward W.D. Whittaker, Joanna A. Mrozinski and Sadaoki Furui.
• Towards Optimal Bayes Decision for Speech Recognition Jen-Tzung Chien a
• A Weight Estimation Method Using LDA for Multi-Band Speech Recognition Koji Iwano, Kaname Kojima, and Sadaoki Furui
• Perplexity Based Linguistic Model Adaptation for Speech Summarisation Pierre Chatain, Edward Whittaker, Joanna Mrozinski, Sadaoki Furui
• Why is Automatic Recognition of Spontaneous Speech So Difficult? Sadaoki Furui, Masanobu Nakamura, and Koji Iwano
• Robust Scene Recognition for Baseball Broadcast Koichi Shinoda and Sadaoki Furui
• SPEECH RECOGNITION USING FHMMS ROBUST AGAINST NONSTATIONARY NOISE Agnieszka Betkowska, Koichi Shinoda, and Sadaoki Furui
• THE EFFECT OF SPECTRAL SPACE REDUCTION IN SPONTANEOUS SPEECH ON RECOGNITION PERFORMANCES
• SEMI-SYNCHRONOUS SPEECH AND PEN INPUT Yasushi Watanabe, Kenji Iwata, Ryuta Nakagawa, Koichi Shinoda, and Sadaoki Furui
• A Robust Scene Recognition System for Baseball Broadcast Using Data-Driven Approach
• Towards Better Language Modeling for Thai LVCSR Markpong Jongtaveesataporn
• Dynamic Language Model Adaptation Using Presentation Slides for Lecture Speech Recognition
• RECENT ADVANCES IN AUTOMATIC SPEECH SUMMARIZATION* Sadaoki Furui
• Development of a Speech Recognition System Using a Sparse Training Corpus Arnar Thor Jensson, Koji Iwano and Sadaoki Furui
• Acoustic and Linguistic Characterization of Spontaneous Speech Masanobu Nakamura, Sadaoki Furui, and Koji Iwano
• An Overview of Question Answering at Tokyo Institute of Technology Edward Whittaker and Sadaoki Furui
• Comparative Study on Robust Speech Recognition against Nonstationary Noise in the Home Environment
• A NEW MUTUAL INFORMATION MEASURE FOR INDEPENDENT COMPONENT ALALYSIS
• Aggregated Cross-validation and Its Efficient Application to Gaussian Mixture Optimization
• THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS
• THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS
• INDEPENDENT COMPONENT ANALYSIS FOR NOISY SPEECH RECOGNITION Hsin-Lung Hsieh1
• GENERALIZATION OF SPECIALIZED ON-THE-FLY COMPOSITION Tasuku Oonishi, Paul R. Dixon, Koji Iwano, Sadaoki Furui
• FAST ACOUSTIC COMPUTATIONS USING GRAPHICS PROCESSORS Paul R. Dixon Tasuku Oonishi Sadaoki Furui
• Recent Development of WFST-Based Speech Recognition Decoder
• Noise robust speech recognition using spectral subtraction and F0 information
• 0.238 (0.648 0.886) 0.014 (0.680 0.694)
• Text-to-speech: xfcfc(i) (i = 1, , N) (1)
• TRECVID[1] . , (High-level feature) .
• User Interface Evaluations for a Multimodal ASR-Driven Train Timetables Application
• An Empirical Comparison of Sphinx and HTK models for Speech Recognition Josef R. Novak Paul R. Dixon Sadaoki Furui
• User identification using Time-of-Flight camera image streams Felipe Gomez-Caballero Takahiro Shinozaki Sadaoki Furui
• Voice Activity Detec-Drivers' Japanese Speech Corpus in a Car Envi-
• Audio information visualization for supporting highlight extraction from home video, by TAKAGI Koichi, KAWADA Ryoichi (KDDI), SHINOZAKI Takahiro and FURUI Sadaoki (Tokyo Institute of
• ( ), Jean-Luc Rouas, Martine Adda-Decker(LIMSI-CNRS), An analysis of the influence of speaking style differences to spectral properties in French by Mayumi
• THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS
• NTCIR-6 CLQA Question Answering Experiments at the Tokyo Institute of Technology
• FINITE-STATE TRANSDUCER BASED MODELING OF MORPHOSYNTAX WITH APPLICATIONS TO HUNGARIAN LVCSR
• Cluster-based Modeling for Ubiquitous Speech Recognition Sadaoki Furui, Tomohisa Ichiba, Takahiro Shinozaki, Edward W.D. Whittaker, and Koji Iwano
• AUTOMATIC SPEECH SUMMARIZATION BASED ON WORD SIGNIFICANCE AND LINGUISTIC LIKELIHOOD
• NEURAL-NETWORK-BASED HMM ADAPTATION FOR NOISY SPEECH Sadaoki Furui and Daisuke Itoh
• ERROR ANALYSIS USING DECISION TREES IN SPONTANEOUS PRESENTATION SPEECH RECOGNITION
• UNSUPERVISED CLASS-BASED LANGUAGE MODEL ADAPTATION FOR SPONTANEOUS SPEECH RECOGNITION
• (MIRU2010) 2010 7 152-8550 2-12-1
• Presentation Scene Retrieval Exploiting Features in Videos Including Pointing and Speech Information
• ACOUSTIC AND LINGUISTIC CHARACTERIZATION OF SPONTANEOUS SPEECH Masanobu Nakamura, Sadaoki Furui, and Koji Iwano
• MODEL OPTIMIZATION FOR NOISE DISCRIMINATION IN HOME ENVIRONMENT Agnieszka Betkowska, Koichi Shinoda, and Sadaoki Furui
• Thai Broadcast News Corpus Construction and Evaluation Markpong Jongtaveesataporn
• A STREAM-WEIGHT OPTIMIZATION METHOD FOR MULTI-STREAM HMMS BASED ON LIKELIHOOD VALUE NORMALIZATION
• Why is the Recognition of Spontaneous Speech Sadaoki Furui, Masanobu Nakamura, Tomohisa Ichiba, and Koji Iwano
• NOISE ROBUST SPEECH RECOGNITION USING F0 CONTOUR EXTRACTED BY HOUGH TRANSFORM
• Progress on a Speaker Adaptable Polyglot Synthesizer Javier Latorre, Koji Iwano, Sadaoki Furui
• Noisy Speech Recognition Based on Robust End-point Detection and Model Adaptation
• 50 years of progress in speech and speaker recognition Sadaoki Furui
• Age estimation using MLLR transform-based features. by Toshiya Wada, Takahiro Shinozaki, Sadaoki Furui (Tokyo Institute of Technology)
• Tree-Structured Noise-Adapted HMM Modeling for Piecewise Linear-Transformation-Based Adaptation
• A Tree-Structured Clustering Method Integrating Noise and SNR for Piecewise Linear-Transformation-Based Noise Adaptation
• X(f, t) S(f, t) N(f, t) |S(f, t)|2
• Monolingual Web-based Factoid Question Answering in Chinese, Swedish, English and Japanese
• Evaluation of a WFST-based ASR System for Train Timetable Information
• PROGRESS ON A LANGUAGE INDEPENDENT APPROACH TO QUESTION ANSWERING Edward Whittaker and Sadaoki Furui
• Robust Scene Recognition Using Scene Context Information for Video Contents Koichi Shinoda, Ryoichi Ando, Sadaoki Furui
• BENCHMARK TEST FOR SPEECH RECOGNITION USING THE CORPUS OF SPONTANEOUS JAPANESE
• A study on robust audio-visual speech recognition
• BIMODAL SPEECH RECOGNITION USING LIP MOVEMENT MEASURED BY OPTICAL-FLOW ANALYSIS
• AN ONLINE INCREMENTAL SPEAKER ADAPTATION METHOD USING SPEAKER-CLUSTERED INITIAL MODELS
• Robust Gait Recognition against Speed Variation Muhammad Rasyid Aqmar, Koichi Shinoda, and Sadaoki Furui
• ANALYSIS ON INDIVIDUAL DIFFERENCES IN AUTOMATIC TRANSCRIPTION OF SPONTANEOUS PRESENTATIONS
• High-Level Feature Extraction Using SIFT GMMs and Audio Models Nakamasa Inoue, Tatsuhiko Saito, Koichi Shinoda, and Sadaoki Furui
• A NEW LEXICON OPTIMIZATION METHOD FOR LVCSR BASED ON LINGUISTIC AND ACOUSTIC CHARACTERISTICS OF WORDS
• THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS
• Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume, pages 2124, New York City, June 2006. c 2006 Association for Computational Linguistics
• STUDY ON SPOKEN INTERACTIVE OPEN DOMAIN QUESTION ANSWERING Chiori Hori, Takaaki Hori, Hideki Isozaki,
• TOKYO INSTITUTE OF TECHNOLOGY Revenue Expenditure
• 23 7 25 Co BaFe2As2 3 45
• "Journal of Physical Chemistry C" PF BL-4C MD
• A Cross-Lingual ILP Solution to Zero Anaphora Resolution Tokyo Institute of Technology
• 23 11 18 "ACM/IEEE Supercomputing 2011 (SC11)"
• Multi-modal Reference Resolution in Situated Dialogue by Integrating Linguistic and Extra-Linguistic Clues
• IPSJ SIG Technical Report Barzilay 1)
• 23 11 21 TSUBAME2.0
• February 17, 2012 Tokyo Institute of Technology