ATR Technical Reports since 1987, # of reports:1656

Since the social sense of copyright is quite different now than it was then, each ATR technical report is modified, excluding the parts that cannot be published because of including intellectual property, published papers, etc. This is done whether or not the cover page said the content was confidential. If you find a report that you do not want to publish, please contact the ATR Technical Report Digitization Project (atr-techfb@atr.jp).

Concerning the conditions above, some of the ATR technical reports cannot be fully displayed, and its title will be “TR-I-0186 :1990.10.30 (Internal Use)” for example. By clicking “TR-I-0186 :1990.10.30”, the limited contents can be seen, and to read full contents, click “Internal Use” with additional password and ID which can be obtained by contacting ATR Technical Report Digitization Project (atr-techfb@atr.jp).

• TR-I-0001 : Automatic Telephone Interpretation: A Basic Study
• TR-I-0002 : Analysis of Telephone Conversations through an Interpreter
• TR-I-0003=TR-A-0004 : Japanese Speech Database with Fine Acoustic-Phonetic Transcriptions
• TR-I-0004 : Phoneme Recognition Method using a Stochastic Approach (HMM)
• TR-I-0005 : Continuous Speech Recognition
• TR-I-0006 : Phoneme Recognition Using Time-Delay Neural Networks
• TR-I-0007 : Collection of Interpreted Telephone Conversation Data
• TR-I-0008 : Classification of Japanese Parts of Speech
• TR-I-0009 : Speech Database Management System and Easy Access Language
• TR-I-0010 : Research Activities of Speech Processing Department April 1986 through October 1987
• TR-I-0011 : Interactive Menu System for Speech Workbench
• TR-I-0012 : Basic Speech Processing/Graphic Modules
• TR-I-0013 : Voice Conversion by Analysis-Synthesis Method
• TR-I-0014 : Genaralizing Unification in Semantic Networks toward Natural Language Understanding
• TR-I-0015 : A Description of English Dialogues by Structural Correspondence Specification Language: SCSL
• TR-I-0016 : Comparison of Telephone and Keyboard Conversation
• TR-I-0017 : Summaries of Workshop on Natural Language Dialogue Interpretation, November 27-28, 1987
• TR-I-0018 : Recognition of Japanese Voiced Stops Using Hidden Markov Models
• TR-I-0019=TR-A-0019 : Manual Segmentation of Spectrogram for the Acoustic- Phonetic Transcriptions in a Japanese Speech Database
• TR-I-0020 : Speech Processing Workbench
• TR-I-0021 : High-speed Spectrogram Viewer on X-window System
• TR-I-0022 : Research Activities of the Natural Language Understanding Department and the Knowledge and Data Base Department (April,1986 through December, 1987)
• TR-I-0023 : Quality Control of Speech by Modifying Formant Frequencies and Bandwidths
• TR-I-0024 : On the Prosodic Characteristics in Various Utterances with Different Speaking Styles
• TR-I-0025 : Prosodic Characteristics and Their Control in Japanese Speech with Various Speaking Styles
• TR-I-0026 : A Method of Analyzing Japanese Speech Act Types (I) - Combining Unification-Based Syntactico-Semantic Analysis and Plan Recognition Inference -
• TR-I-0027 : Automatic Idiom Extraction from Text Database
• TR-I-0028=TR-A-0026 : Speech Database User's Manual
• TR-I-0029 : Semantics Relations for the Language Database
• TR-I-0030 : Analysis and Prediction of Vowel-Devocalization in Isolated Japanese Words
• TR-I-0031 : Preliminary Research on the Interface between Speech Recognition and Natural Language Processing
• TR-I-0032 : A Study on Feature Structures and Unification
• TR-I-0033 : A Phoneme Lattice Parsing for Continuous Speech Recognition
• TR-I-0034 : Modularity and Scaling in Large Phonemic Neural Networks
• TR-I-0035 : Representation and computation of units of translation for Machine Interpretation of spoken texts
• TR-I-0036 : An Integrated Linguistic Database Management System
• TR-I-0037 : Speech Workbench Ver.3
• TR-I-0038 : Word Order of Japanese Honorific Predicate Constituents - Explanation by Unification-Based Phrase Structure Grammar-
• TR-I-0039 : How to Make Correct Lexical Descriptions Easily
• TR-I-0040 : Improvement of prosody controls for speech synthesis by rule system
• TR-I-0041 : The Formalization of a Knowledge Base for English
• TR-I-0042 : Prediction of the Next Utterance in a Task-Oriented Dialogue
• TR-I-0043 : Corresponding Japanese and English Text for Linguistic Database
• TR-I-0044 : Record of Six Work Sessions on Concepts, Methods, and Tools from Existing Running Real-Size MT Systems
• TR-I-0045 : Operations on Typed Feature Structures:Motivations and Definitions
• TR-I-0046 : キーボード会話収録システムについて
• TR-I-0047 : English Word Recognition By HMM
• TR-I-0048 : English Speech Database
• TR-I-0049 : Japanese Sentence Analysis by means of Phrase Structure Grammar
• TR-I-0050 : Duration control methods for HMM phoneme recognition
• TR-I-0051 : On sentence level factors gaverning segmental duration in Japanese
• TR-I-0052 : A Study of English Word Category Prediction Based on Neural Networks
• TR-I-0053 : On the unit selection measure for speech synthesis by rule using multiple synthesis units
• TR-I-0054 : Pragmatic Extensions to Unification-Based Formalisms.
• TR-I-0055 : Typed Feature Structures II The Language and its Implementation
• TR-I-0056 : Outline of Japanese Speech Database for Synthesis
• TR-I-0057 : Word Spotting Method Based on HMM Phoneme Recognition
• TR-I-0058 : Fast Back-Propagation Learning Methods for Neural Networks in Speech
• TR-I-0059 : DyNet, a Fast Program for Learning in Neural Networks
• TR-I-0060 : Erectronic Mail and News User's Manual
• TR-I-0061 : Speech Research at ATR Interpreting Telephony Research Laboratories
• TR-I-0062 : An Experimental Study on English Sentence Generation System for the Natural Dialogue Translation
• TR-I-0063=TR-A-0040 : Neural Networks Applied to Speech Processing
• TR-I-0064 : A Study on Unification-Based Phrase Structure Grammar Parser with Rule Application Control
• TR-I-0065 : Research Activities of the Speech Processing Department November 1987 through December 1988
• TR-I-0066 : Modified MITalk
• TR-I-0067 : Tri-Layered Plan Recognition Model for Dialogue Machine Translation
• TR-I-0068 : Extracting Domain Knowledge from Goal Oriented Dialogues
• TR-I-0069 : Tools for Fundamental Frequency Modelling
• TR-I-0070 : Research Activities of the Natural Language Understanding Department and the Knowledge and Data Base Department for 1988
• TR-I-0071 : RETIF -- A Rewriting System for Typed Feature Structures --
• TR-I-0072 : Phoneme Segmentation Expert System Using Spectrogram Reading Knowledge
• TR-I-0073 : Phoneme segmentation knowledge based on spectrogram reading
• TR-I-0073_appendix : Phoneme segmentation knowledge based on spectrogram reading(appendix)
• TR-I-0074 : The ATMS Manual Version 1.1
• TR-I-0075 : Politeness Strategies in American English Telephone Dialogues
• TR-I-0076 : Study of HMM Duration Parameter Adaptation for HMM-LR Speech Recognition System
• TR-I-0077 : User's Manual for Morpheme Information
• TR-I-0078 : Pitch frequency database on continuous speech
• TR-I-0079 : Integrating linguistic and prosodic information in a continuous speech database
• TR-I-0079_appendix : Integrating linguistic and prosodic information in a continuous speech database (Separated Appendix)
• TR-I-0080 : A Study on the Understanding of Negative Sentences
• TR-I-0081 : An approach for normalizing coarticulatory variations through expansion of acoustic properties into phonetic features
• TR-I-0082 : HMM Continuous Speech Recognition Using Generalized LR Parsing
• TR-I-0083 : Utterance Interpretation based on Constraints on Dialogue Participants' Mental States
• TR-I-0084 : The E-Mail & News Adminstrator's Manual
• TR-I-0085 : Continuous Speech Recognition Using TDNN Phoneme Spotting and Generalized LR Parser
• TR-I-0086 : Construction of ATR Japanese Speech Database as A Research Tool
• TR-I-0086_appendix1 : Construction of ATR Japanese Speech Database as A Research Tool (Appendix I)
• TR-I-0086_appendix2 : Construction of ATR Japanese Speech Database as A Research Tool (Appendix II)
• TR-I-0087 : Characteristics of a Japanese Phoneme 'Sokuon'
• TR-I-0089 : Spotting Phonemes and Syllables Using Time-Delay Neural Networks
• TR-I-0090 : Parallelism, Hierarchy, Scaling in Time-Delay Neural Networks for Spotting Phonemes and CV-Syllables
• TR-I-0091 : Xll Pocket Guide - Xlib -
• TR-I-0092 : X11 Pocket Guide - X Toolkit-
• TR-I-0093 : The Feature Structure Rewriting System Manual
• TR-I-0094 : Noun Phrase Identification in Dialogue and its Applications
• TR-I-0095 : Speaker Adaptation through Separate Vector Quantiazation
• TR-I-0096 : Speaker Adaptation through Fuzzy Vector Quantiazation
• TR-I-0097 : VQ-based Speaker Adaptation Applied to HMM Phoneme Recognition
• TR-I-0098 : VQ-based Speaker Adaptation Applied to Time Delay Neural Network Phoneme Recognition
• TR-I-0099 : Speaker Adaptation of Articulatory Variation by Supplemented HMM
• TR-I-0100 : A Study of VQ-based Speaker Adaptation
• TR-I-0101 : A Comparative Study of Spectral Mapping Method on Speaker Adaptation
• TR-I-0102 : Spoken Language Translation Experimental System from Japanese to English
• TR-I-0103 : Effective Training Methods for Spotting Japanese Phonemes Using Time-Delay Neural Networks
• TR-I-0104 : Inferring the Omitted Words Using Valency Patterns
• TR-I-0105 : Generating the Function Words Using the Probability of Bigram Model
• TR-I-0106 : An Automatic Hardcopy Tool Based on Speech Work Bench
• TR-I-0107 : Phoneme Recognition Using Neural Prediction Models
• TR-I-0108 : English Word Recognition By HMM Using Multiple Codebooks
• TR-I-0109 : Selecting the Phrase Candidates Using Dependency Relationship
• TR-I-0110 : Selecting the Phrase Candidates in SL-TRANS
• TR-I-0111 : Dependency Relationship Database for Selecting the Phrase Candidates
• TR-I-0112 : Speech Synthesis by Rule for Convention, and Applying Neural Networks to Continuous Speech
• TR-I-0113 : Neural Net Workbench System
• TR-I-0114 : Multiple Inheritance in RETIF
• TR-I-0115 : Research Activities of the Speech Processing Department January 1989 through October 1989
• TR-I-0116 : ON INTERPRETATIONS OF A FEED-FORWARD NEURAL NETWORK
• TR-I-0117 : Identifying Zero-Pronouns Referring to Persons in Japanese Dialogue
• TR-I-0118 : Research Activities of the Natural Language Understanding Department and the Knowledge and Data Base Department for Feb. 1989~Oct. 1989
• TR-I-0119 : A new method to speed up the Back-Propagation algorithm
• TR-I-0120 : Connectionist Large Vocabulary Word Recognition
• TR-I-0121 : Evaluation of the output in Japanese to English MT systems
• TR-I-0121_appendix : Evaluation of the output in Japanese to English MT systems
• TR-I-0122 : Constructive Neural Network for Speech Recognition
• TR-I-0123 : English Word Recognition Using HMM Phone Concatenated Training and NETgram
• TR-I-0124 : Efficient Disjunctive Unification in a Bottom-Up Shift-Reduce Parser
• TR-I-0125 : Sketch of a bunsetsu-based unification grammar for Japanese with particular reference to adjuncts
• TR-I-0126 : Cross-Language Voice Conversion
• TR-I-0127 : Unit extraction context and inter-unit discontinuities
• TR-I-0128 : Known Current Problems In Automatic Interpretation: Challenges for Language Understanding
• TR-I-0129 : Strategic Lazy Incremental Copy Graph Unification Method
• TR-I-0130 : Shift-invariant Deterministic Boltzmann Machines for Phoneme Recognition
• TR-I-0131 : HMM音韻認識における音韻連鎖情報の利用
• TR-I-0132 : Current Status and Problems of SL-TRANS
• TR-I-0133 : Improvement of HMM-based English Word Recognition using NETgram
• TR-I-0134 : Local Cohesive Knowledge
• TR-I-0135 : Quality evaluation for synthesized speech using wave overlap adding
• TR-I-0136 : On the Concatenation of Speech Synthesis Units According to Unit Extraction context
• TR-I-0137 : The MapSignal remote speech editor
• TR-I-0138 : Experiments in pitch extraction
• TR-I-0139 : Auditory nerve fiber spike generation model
• TR-I-0140 : Speech Synthesis System Using Non-Uniform Units.
• TR-I-0140_appendix : Speech Synthesis System Using Non-Uniform Units.
• TR-I-0141 : Estimation of Grammar Probabilities from Text Database
• TR-I-0142 : Evaluation and Diagnosis of Selective Use of Non-uniform Units for Speech synthesis-by-rule.
• TR-I-0143 : Automatic Rule Derivation for Speech Synthesis from Large-scaled Speech Database
• TR-I-0144 : Large Vocabulary Spoken Word Recognition Using Time-Delay Neural Network Phoneme Spotting and Predictive LR-Parsing
• TR-I-0145 : TDNNの構造の音韻認識率、シフトイバリアント性への影響
• TR-I-0146 : A keyboard dialogue analysis tool
• TR-I-0147 : Phoneme Recognition Using Hidden Markov Models
• TR-I-0148 : HMM Phoneme recognition Using Syallable Trigrams
• TR-I-0149 : 種々の発話様式における韻律制御の検討
• TR-I-0150 : ATR's Linguistic Database Structure
• TR-I-0151 : Corresponding Japanese and English Text for Linguistic Database II
• TR-I-0152 : Specifications of Corresponding Japanese and English Text for Linguistic Database
• TR-I-0153 : A Retrieval System For The ADD (ATR's Linguistic Database)
• TR-I-0154 : A Retrieval System for The ADD (ATR's Linguistic Database) User's Manual
• TR-I-0155 : Semantic representations used in Japanese analysis grammar
• TR-I-0156 : A Japanese Grammar for SL-TRANS
• TR-I-0157 : Token Count Statistics Extracted from the ATR Dialogue Database
• TR-I-0158 : Accent of Sino-Japanese Complex Word and the Number of Characters
• TR-I-0159 : Factor analysis of vowel devoicing in Japanese
• TR-I-0160 : A study on F0 patterns and prosodic units
• TR-I-0161 : Generalized LR Parsing in Hidden Markov Model
• TR-I-0162 : The FS-LF Manual Version 1.2
• TR-I-0163 : A Parallel Method For Unification-based Parsers
• TR-I-0164 : Time-Frequency Spectral Estimation of Speech - The Role of Variance In Estimator Performance
• TR-I-0165 : ABMT for Text and Dialogue: a preliminary assessment of its potentials
• TR-I-0166 : Speech Database User's Manual
• TR-I-0167 : AUTOMATIC LANGUAGE RECOGNITION USING ACOUSTIC FEATURES
• TR-I-0168 : Reduction of Speech Recognition Candidates by Statistical Method
• TR-I-0169 : Efficiency of Regular Grammar for Speech Recognition
• TR-I-0170 : Design Principle of Language Model for Speech Recognition
• TR-I-0171 : Work Bench Toolkit Widget
• TR-I-0172 : 品詞情報による音韻継続時間長の分析
• TR-I-0173 : Neural Networks applied to Speech Processing in ATR
• TR-I-0174 : Study on Combining HMMs and Neural Network Models -- TDNN-HMM for Phoneme recognition --
• TR-I-0175 : Voice Quality Conversion and A High Quality Pitch Modification
• TR-I-0176 : English Word Category Prediction Based on Neural Network
• TR-I-0177 : Vowel Recognition by Phoneme Filter Neural Networks
• TR-I-0178 : Speaker-Independent Phoneme Recognition Using Time-Delay Neural Networks
• TR-I-0179 : Some Computational Applications of Lexical Functions
• TR-I-0180 : 並列自然言語処理における単一化手法の高速化
• TR-I-0181 : Procedure to Create a Knowledge Base which Describes Intermediate Concepts
• TR-I-0182 : ATR Symposium on Basic Research for Telephone Interpretation
• TR-I-0182_appendix : ATR Symposium on Basic Research for Telephone Interpretation
• TR-I-0183 : 発話変動にロバストなTDNNの検討
• TR-I-0184 : Overview of ATR Basic Researches into Telephone Interpretation
• TR-I-0185 : A Machine Discrimination of Subject and Object in A Japanese - English Translation
• TR-I-0186 : Contents of the ATR Dialogue Database
• TR-I-0187 : Feature Structure Rewriting System Manual (Revised Version)
• TR-I-0188 : Details of the transfer process in the ST-TRANS translation system
• TR-I-0189 : A Design for a Disambiguation-Based Dialog Understanding System
• TR-I-0190 : A Fuzzy Training Approach for Phoneme Classification Neural Networks
• TR-I-0191 : A STUDY ON SPEAKER INDIVIDUALITY CONTROL
• TR-I-0192 : Neural Net Workbench System
• TR-I-0193 : Syntactic Rules for Speech Recognition in SL-TRANS
• TR-I-0194 : The Structure and the Inference Method of a Knowledge Base which Describes the Co-occurrence between Words
• TR-I-0195 : Vowel Duration Control using Linguistic Information
• TR-I-0196 : A Bilingual Dialogue Database for Automatic Spoken Language Interpretation between Japanese and English
• TR-I-0197 : MONA-LISA: Multimodal Ontological Neural Architecture for Linguistic Interactions and Scalable Adaptations
• TR-I-0198 : Quasi-Destructive Graph Unification
• TR-I-0199 : A Context Processing Mechanism for a Dialogue Translation System
• TR-I-0200 : A Dialogue Understanding Mechanism: A Model of Contextual Negations
• TR-I-0201 : The Experiment of a dialogue translation system
• TR-I-0202 : Study of Speaker Independent Speech Recognition
• TR-I-0203 : Speech Recognition Using Supplemented HMM
• TR-I-0204 : Application of the Hierarchial Clustering Method to the Translated Word Selection
• TR-I-0205 : PARTs: A Machine Translation System by composing dependency units
• TR-I-0206 : Typed-Feature-Structure-Directed Generation
• TR-I-0207 : Optimization of Unification based Generation
• TR-I-0208 : English Grammar for Unification-Based Parser/Generator
• TR-I-0209 : Connectionist Large-Vocabulary Continuous Speech Recognition
• TR-I-0210 : A Study of Speech Recognition Using Neural Networks --- A Collection of Papers ---
• TR-I-0211 : TDNN-HMM-LR Applied to Phrase Recognition
• TR-I-0212 : Japanese-English Linguistic Recognition Using Bilingual Speakers
• TR-I-0214 : 対判定型ニューラルネットワークの原理と 時間遅れ神経回路網との統合による ロバストな音素認識
• TR-I-0215 : Smoothing Technique of Matching Score of Dependencies using Semantic Word Categorization
• TR-I-0216 : Comparing Fricatives: A Spectral Analysis of /hi/ and /ç/ in Japanese and German
• TR-I-0217 : Detailed Rules for Japanese Morphological Analysis
• TR-I-0218 : Distribution of Knowledge Data Extracted from a Language Data Base
• TR-I-0219 : Speaker Independent Phoneme Recognition Using Time-Delay Neural Networks
• TR-I-0220 : Connections Between Surface Sentence Forms and Speaker's Intentions in Cooperative Task-Oriented Conversations - Classification of Communicative Acts Relied on Surface Forms -
• TR-I-0221 : Spectral Interpolation using Distortion Geodesic Lines
• TR-I-0222 : Unsupervised Speaker Adaptation Using VQ Neural Network
• TR-I-0223 : A Study on Noise Robust VQ Codebook Generation
• TR-I-0224 : Evaluation of Speech Recognition Candidates by Statistical Methods
• TR-I-0225 : Report on working discussions and ongoing research
• TR-I-0226 : Langauge Identification Using Probabilistic Modeling
• TR-I-0227 : An Optimization of Speaker Mapping Neural Network Using Mimimal Error Criterion
• TR-I-0228 : Tools for Monitoring Parallel Lisp Programs
• TR-I-0229 : Unification-Based Parsing on Increasing Levels of Parallelism
• TR-I-0230 : Research Activities of the Speech Processing Department November 1989 through December 1990
• TR-I-0231 : Research Activities of the Natural Language Understanding Department and the Data Processing Department for Nov. 1989-Mar. 1991
• TR-I-0232 : An algorithm of generating a phoneme-context-dependent CFG for HMM-LR continuous speech recognition.
• TR-I-0233 : Text-Independent Speaker Recognition Using Neural Networks
• TR-I-0234 : "Quasi-Destructive Graph Unification with Structure-Sharing"
• TR-I-0235 : Determining Surface Form for Indirect Speech Acts in English
• TR-I-0236 : HMMを用いた言語のモデル化に関する基礎実験
• TR-I-0237 : Evaluation of metrics for text comparison with implication for recognition
• TR-I-0238 : Automatic Phoneme Segmentation Using Continuous Hidden Markov Models
• TR-I-0239 : Speaker Adaptation using Context-dependent Continuous Density Hidden Markov Models
• TR-I-0240 : 音声認識のための構文規則 ガイドブック
• TR-I-0241 : Expansion of Syntactic Rules for Speech Recognition in SL-TRANS
• TR-I-0242 : Speech Recognition Expert System -- A Study on Knowledge and Neural Networks Intragration --
• TR-I-0243 : A Study on Expert System and Neural Nets for Speech Recognition - Collection -
• TR-I-0244 : The Role of Accessibility and Identifiability in Accounting for Japanese Zero Pronouns
• TR-I-0245 : Differences in Part-of-Speech and Lexical Items between the Speech Recognizer, the Morphological Analyzer, and the Parser in ATR
• TR-I-0246 : HMM-LR User's Manual
• TR-I-0247 : The Beholder TOOLBOX Manual -- Part 1 --
• TR-I-0248 : A Study on the Adaptive Search Methods in HMM-LR Continuous Speech Recognition
• TR-I-0249 : Radial Basis Function-Based Fuzzy Partition Models Aiming at Speech Recognition
• TR-I-0250 : An Overview of a General-Purpose Japanese Dictionary
• TR-I-0251 : A Study on Semantic Information for a General-Purpose Japanese Dictionary
• TR-I-0252 : Connections Between Surface Sentence Forms and Speaker's Intentions in Cooperative Task-Oriented Conversations - Communicative Act Type Extraction System using Rules on Japanese Sentence-final Surface Expressions -
• TR-I-0253 : A method to predict the next utterance using a layered plan recognition model
• TR-I-0254 : Communicative Act Type Extractor
• TR-I-0255 : (LAYered pLAn recognition system)
• TR-I-0256 : DIscourse ANAlyzor
• TR-I-0257 : 分散処理機構実現のための 変換主導型機械翻訳評価実験
• TR-I-0258 : A Basic Introduction to Planning and Meta-Decision-Making with Uncertain Nondeterministic Actions using Second-Order Probabilities
• TR-I-0259 : Managing Contextual Information for Discourse Interpretation
• TR-I-0260 : Communicative Functions of Spoken Japanese and Its Meaning Interpretation on MT System
• TR-I-0261 : Research Activities of The Speech Processing Department January through December, 1991
• TR-I-0262 : N-Source Decomposition Problem
• TR-I-0263 : A Study of Speaker Adaptation and Speaker Individuality
• TR-I-0264 : Third Person Referring Expressions in English
• TR-I-0265 : A study of speech recognition using speaker selection approach
• TR-I-0266 : Speaker adaptation based on transfer vector field smoothing model with continuous mixture density HMMs
• TR-I-0267 : Discourse Management Mechanism on Spoken Dialogue Processing (in an MT System)
• TR-I-0269 : English-Japanese Transfer by ASURA Framework (interim report)
• TR-I-0270 : HMM-LRソース・コード
• TR-I-0271 : HMM-LR音声認識プログラム ユーザーズ・マニュアル
• TR-I-0272 : Users'Manual for Japanese Morphological Analysis and Related Programs
• TR-I-0273 : A Study on Language Modeling for Speech Recognition
• TR-I-0275 : Neural Net Workbench System User's Manual
• TR-I-0276 : Tree-based Unit Selection for English Speech Synthesis
• TR-I-0278 : A Study on the orthography of Japanese in SL-TRANS
• TR-I-0279 : Language Model Using N-grams for Particles and Its Application to Speech Recognition
• TR-I-0280 : Sentence Type Recognition Using Sentence Final Pitch Contour
• TR-I-0281 : Research Activities of the Natural Language Understanding Department and the Data Processing Department for Apr. 1991-Mar. 1992
• TR-I-0282 : 機能分割とパイプラインによる機 械翻訳システムの並列処理手法
• TR-I-0283 : Composition of Noise and Clean-Speech HMMs for Recognition of Noisy Speech
• TR-I-0284 : Evaluation of speaker adaptation method based on transfer vector field smoothing model with continuous mixture density HMMs
• TR-I-0285 : ATR ν-Talk Speech Synthesis System
• TR-I-0286 : Speech Database User's Manual for Synthesis
• TR-I-0287 : Automated Labelling of Prosodic Aspects of English Speech: Final Report
• TR-I-0288 : An Introduction to Unification-Based Parsing Techniques
• TR-I-0289 : The German Grammar for ASURA
• TR-I-0290 : Radial Basis Function-Based Fuzzy Partition Models Aiming at Speech Recognition
• TR-I-0291 : Variance Spreading for Better Recognition using HM-Nets : a deterministic approach
• TR-I-0292 : A Study on Dynamic Speaker Adaptation using HMM-Nets
• TR-I-0293 : Easier C programming Input/output facilities
• TR-I-0294 : Easier C programming Some useful objects
• TR-I-0295 : Easier C programming Dynamic programming
• TR-I-0296 : Speaker-Independent Features Extracted by a Neural Network and Their Evaluation in Speech Recognition
• TR-I-0297 : Instruction Duration Timing Results for the Sequent Symmetry Parallel Computer
• TR-I-0298 : First Steps Toward Annotating Illocutionary Force Types to a Bilingual Dialogue Corpus
• TR-I-0299 : Demonstration Manual in ATR ITL/Speech Processing Department
• TR-I-0300 : Computer & Software User's Guide in ATR ITL/Speech Processing Department
• TR-I-0301 : Specifications of Semantics Relations for ATR Dialogue Database - for deep cases -
• TR-I-0302 : Manual for Speech Input Programs: SpeechIn, SpeechPress
• TR-I-0303 : Implementation of ATR Speech Translation System: ASURA
• TR-I-0304 : Evaluation of ATR Speech Translation System: ASURA
• TR-I-0305 : HMMとエキスパートシステムの手法を用いた 音素セグメンテーションシステムと ラベリングワークベンチ
• TR-I-0306 : Telephone speech recognition using continuous HMMs with clean speech data
• TR-I-0307 : Japanese-to-English Transfer-Driven Machine Translation System
• TR-I-0308 : Retrieved Data from ATR Corpus for Building Transfer Knowledge
• TR-I-0309 : 3年間の音声情報処理研究をふりかえって -- 音声情報処理研究および研究支援業務概観 --
• TR-I-0310 : Labelling Workbench version 1.0 - User's Guide -
• TR-I-0311 : User's Guide: Semantic Distance Calculator
• TR-I-0312 : Research Activities of the Natural Language Understanding Department and the Data Processing Department for Apr. 1992-Jan. 1993
• TR-I-0313 : Research Activities of the Speech Processing Department -- January through December, 1992 --
• TR-I-0314 : A Study on Unsupervised and Supervised Speaker Adaptation
• TR-I-0315 : Speech Recognition Based on Vector Field Model Adaptation In a Noisy Environment
• TR-I-0316 : Comparison among WLR,WGD and SGDS distance measure under noisy environment with HMM-LR
• TR-I-0317 : Morphological Analysis Specifications for the ATR Dialogue Database
• TR-I-0318 : Example-Based Machine Translation on a Massively Parallel Associative Processor, IXM2
• TR-I-0319 : "A Study on the Parallel Implementation by Data Distribution in Example-based Machine Translation"
• TR-I-0320 : "A Study on the Effective Measure by Shannon's Information Value in Example-based Machine Translation"
• TR-I-0321 : Specifications of Dependency Relations for ATR Dialogue Database - for surface cases -
• TR-I-0322 : Dialog Analysis Program User's Manual
• TR-I-0323 : (LAYered pLAn recognition system) User's Manual
• TR-I-0324 : SSS-ToolKit(Ver1.0)User's Manual
• TR-I-0325 : Continuous Speech Recognition Based on Context-Free Grammars
• TR-I-0326 : Evaluation of Japanese Morphological Analysis for ATR Dialogue Database
• TR-I-0327 : A Study of Speaker Adaptation and Speaker-Independent Continuous Speech Recognition Using Neural Networks - A List of Papers -
• TR-I-0328 : The ATR-CMU Conference Registration Task Speech DataBase - User's Guide -
• TR-I-0329 : The Japanese-English Transfer Rules for ASURA
• TR-I-0330 : Synopsis of Language Transfer Engine for ASURA - Sytem and Users Manual for Feature Structure Rewriting System V2 -
• TR-I-0331 : Current Status of Language Transfer Processing for Spoken Dialogue Translation
• TR-I-0332 : The Target Corpus of ASURA
• TR-I-0333 : An Empirical Study on Unification-Based Parsers
• TR-I-0334 : Development History of the Unification-Based Spoken-Style Japanese Grammar for ASURA
• TR-I-0335 : User's Guide to the Unification-Based Spoken-Style Japanese Grammar for ASURA
• TR-I-0336 : A Study of Noisy Speech Recognition and Speaker adaptation
• TR-I-0337 : Expansion of Syntactic rules for Speech Recognition in ASURA
• TR-I-0338 : Execution Report of International Joint Experiment toward Interpreting Telephony
• TR-I-0339 : SSS-LR連続音声認識システム - User's Guide -
• TR-I-0340 : Collection of the Dialogues for the ATR Dilogue Database (with transcriptions)
• TR-I-0341 : Evalution of Translation in ASURA
• TR-I-0342 : The Need for Second-order Probability Distributions Under Repeated Trials with Nonlinear Utilities or Catastrophic Outcomes
• TR-I-0343 : The FLAIL Expert System Shell Manual
• TR-I-0344 : Transfers of Short Answers From Japanese into English Using a Context-dependent Plan Inference System
• TR-I-0345 : The Meanings of Ability Utterances with Applications to Dialog Understanding
• TR-I-0346 : A Grammar for Japanese Generation in the TUG Framework
• TR-I-0347 : Speech Analysis and Phoneme Label Conversion for Speech Recognition Research
• TR-I-0348 : S/Splus for Speech Processing Research at ATR/ITL
• TR-I-0349 : Japanese generation within ASURA framework
• TR-I-0350 : ATR自動翻訳電話研究所における 音声情報処理の研究
• TR-I-0351 : An English Analysis Grammar in a Unification-based Framework
• TR-I-0352 : 音声データ・ラベリング・マニュアル Speech data・Labeling・Manual
• TR-I-0353 : A Study of English Pronunciation by Japanese Speakers through the Spectrographic Analysis - Special Reference to /r/ vs /l/ and /b/ vs /v/ -
• TR-I-0354 : A Study of Japanese Consonants through the Successive State Splitting (SSS) Algorithm
• TR-I-0355 : Continuous Mixture HMnet for Speaker-Independent Speech Recognition User's Manual
• TR-I-0356 : trigram sentence recognition system User's Manual
• TR-I-0357 : Speech Recognition Using Particle Bigrams and Content-Word Bigrams - User's Manual -
• TR-I-0358 : Speech Database for Evaluation of Recognition Systems
• TR-I-0359 : English Generation Rules for ASURA
• TR-I-0360 : LRパーザの応用法
• TR-I-0361 : Morphological Synthesis in ASURA: Reference Manual
• TR-I-0362 : Morphological Facilities for German Generation in ASURA
• TR-I-0363 : The ATR British English Speech Database
• TR-I-0364 : Continuous Mixture HMM-LR User's Manual
• TR-I-0365 : A Japanese-German Transfer Component for ASURA
• TR-I-0366 : An All-phoneme Ergodic HMM User's Manual
• TR-I-0367 : The NP Manual Version 3.1
• TR-I-0368 : Results of the ABDUCK Disambiguation System
• TR-I-0369 : The B-SURE MANUAL Version 2.3
• TR-I-0370 : Multi-Agent Communication and Commitment and The BEHOLDER family of algorithms for scheduling multiple parallel uncertain processes under limited-resource conditions
• TR-I-0371 : A Sarvey of Data Retrieval from the ATR Dialogue Database
• TR-I-0372 : Research Activities of the Speech Processing Department -- January through March, 1993 --
• TR-I-0373 : Supplement to Collected Papers of the Speech Processing Department 1993
• TR-I-0374 : Research Activities of the Natural Language Understanding Department and the Data Processing Department for February 1993 March 1993
• TR-I-0375 : User's Manual for the HMM-LR Implemented Using Various Search Techniques
• TR-I-0376 : Performance of the Generation Module for ASURA
• TR-I-0377 : FBI: A program for inferring stochastic grammar rules from example text