List of Accepted Papers
Following is the list of accepted SLT 2014 papers, sorted by paper title. You can use the search feature of your web browser to find your paper number. Notifications to all authors have also been sent by email. If you have not received your notification of the results by email, please contact us at papers@slt2014.org.
Poster presentations: The maximum poster size is 6 feet wide by 4 feet tall (landscape).
| 1162 | A COMPARISON OF ACOUSTIC-PROSODIC ENTRAINMENT IN FACE-TO-FACE AND REMOTE COLLABORATIVE LEARNING DIALOGUES |
| 1069 | A COMPLETE KALDI RECIPE FOR BUILDING ARABIC SPEECH RECOGNITION SYSTEMS |
| 1137 | A DATA-DRIVEN PHONEME MAPPING TECHNIQUE USING INTERPOLATION VECTORS OF PHONE-CLUSTER ADAPTIVE TRAINING |
| 1023 | A DISCRIMINATIVE MODEL BASED ENTITY DICTIONARY WEIGHTING APPROACH FOR SPOKEN LANGUAGE UNDERSTANDING |
| 1167 | A DISCRIMINATIVE SEQUENCE MODEL FOR DIALOG STATE TRACKING USING USER GOAL CHANGE DETECTION |
| 1198 | A DISTRIBUTED ARCHITECTURE FOR FAST SGD SEQUENCE DISCRIMINATIVE TRAINING OF DNN ACOUSTIC MODELS |
| 1056 | A GENERALIZED RULE BASED TRACKER FOR DIALOGUE STATE TRACKING |
| 1123 | A KEYWORD SEARCH SYSTEM USING OPEN SOURCE SOFTWARE |
| 1245 | A METHODOLOGY FOR USING CROWDSOURCED DATA TO MEASURE UNCERTAINTY IN NATURAL SPEECH |
| 1159 | A MULTIMODAL STROKE-BASED PREDICTIVE INPUT FOR EFFICIENT CHINESE TEXT ENTRY ON MOBILE DEVICES |
| 1010 | A SPARSITY BASED PREPROCESSING FOR NOISE ROBUST SPEECH RECOGNITION |
| 1118 | A WORD-LEVEL TOKEN-PASSING DECODER FOR SUBWORD N-GRAM LVCSR |
| 1036 | ACQUISITION OF ORDINAL WORDS USING WEAKLY SUPERVISED NMF |
| 1085 | ADOLESCENT SUICIDAL RISK ASSESSMENT IN CLINICIAN-PATIENT INTERACTION: A STUDY OF VERBAL AND ACOUSTIC BEHAVIORS |
| 1044 | AN EFFICIENT ERROR CORRECTION INTERFACE FOR SPEECH RECOGNITION ON MOBILE TOUCHSCREEN DEVICES |
| 1234 | AN END-TO-END DIALOG SYSTEM FOR TV PROGRAM DISCOVERY |
| 1075 | ANNEALED DROPOUT TRAINING OF DEEP NETWORKS |
| 1026 | ANNOTATING VIDEO LECTURES WITH LEARNING STANDARDS |
| 1191 | ARTIFICIAL NEURAL NETWORK FEATURES FOR SPEAKER DIARIZATION |
| 1143 | AUTHOR-TOPIC BASED REPRESENTATION OF CALL-CENTER CONVERSATIONS |
| 1089 | AUTOMATIC SELECTION OF SPEAKERS FOR IMPROVED ACOUSTIC MODELLING: RECOGNITION OF DISORDERED SPEECH WITH SPARSE DATA |
| 1024 | BACKGROUND-TRACKING ACOUSTIC FEATURES FOR GENRE IDENTIFICATION OF BROADCAST SHOWS |
| 1083 | BAYESIAN RECURRENT NEURAL NETWORK LANGUAGE MODEL |
| 1251 | BILINGUAL RECURRENT NEURAL NETWORKS FOR IMPROVED STATISTICAL MACHINE TRANSLATION |
| 1152 | BUT ASR SYSTEM FOR BABEL SURPRISE EVALUATION 2014 |
| 1105 | CLASSIFICATION OF LEXICAL STRESS PATTERNS USING DEEP NEURAL NETWORK ARCHITECTURE |
| 1126 | COMBINING LOCAL AND BROAD TOPIC CONTEXT TO IMPROVE TERM DETECTION |
| 1073 | COMPUTATIONAL ANALYSIS OF TRAJECTORIES OF LINGUISTIC DEVELOPMENT IN AUTISM |
| 1158 | CONSTRAINED SPEAKER DIARIZATION OF TV SERIES BASED ON VISUAL PATTERNS |
| 1131 | CONTEXT-BASED RECOGNITION NETWORK ADAPTATION FOR IMPROVING ON-LINE ASR IN AIR TRAFFIC CONTROL |
| 1201 | DATA COLLECTION AND LANGUAGE UNDERSTANDING OF FOOD DESCRIPTIONS |
| 1247 | DEEP CONVOLUTIONAL NETS AND ROBUST FEATURES FOR REVERBERATION-ROBUST SPEECH RECOGNITION |
| 1072 | DEEP ORDER STATISTIC NETWORKS |
| 1232 | DERIVING LOCAL RELATIONAL SURFACE FORMS FROM DEPENDENCY-BASED ENTITY EMBEDDINGS FOR UNSUPERVISED SPOKEN LANGUAGE UNDERSTANDING |
| 1214 | DISCRIMINATION BETWEEN SINGING AND SPEECH IN REAL-WORLD AUDIO |
| 1207 | DISTRIBUTED OPEN-DOMAIN CONVERSATIONAL UNDERSTANDING FRAMEWORK WITH DOMAIN INDEPENDENT EXTRACTORS |
| 1057 | DOCUMENT-BASED DIRICHLET CLASS LANGUAGE MODEL FOR SPEECH RECOGNITION USING DOCUMENT-BASED N-GRAM EVENTS |
| 1041 | DOMAIN INVARIANT SPEECH FEATURES USING A NEW DIVERGENCE MEASURE |
| 1091 | DYNAMICALLY SUPPORTING UNEXPLORED DOMAINS IN CONVERSATIONAL INTERACTIONS BY ENRICHING SEMANTICS WITH NEURAL WORD EMBEDDINGS |
| 1029 | DYSARTHRIC VOCAL INTERFACES WITH MINIMAL TRAINING DATA |
| 1099 | EFFECTIVE COMBINATION OF HETEROGENEOUS SUBWORD-BASED SPOKEN TERM DETECTION SYSTEMS |
| 1211 | EFFECTIVE DATA-DRIVEN FEATURE LEARNING FOR DETECTING NAME ERRORS IN AUTOMATIC SPEECH RECOGNITION |
| 1092 | EFFICIENT MULTI-LINGUAL UNSUPERVISED ACOUSTIC MODEL TRAINING UNDER MISMATCH CONDITIONS |
| 1065 | EM-BASED PHONEME CONFUSION MATRIX GENERATION FOR LOW-RESOURCE SPOKEN TERM DETECTION |
| 1086 | EMOTION RECOGNITION ON INDONESIAN TELEVISION TALK SHOWS |
| 1053 | ENTITY RANKING FOR DESCRIPTIVE QUERIES |
| 1268 | EVALUATION OF SYLLABLE RATE ESTIMATION IN EXPRESSIVE SPEECH AND ITS CONTRIBUTION TO EMOTION RECOGNITION |
| 1032 | EXEMPLAR-BASED NOISE ROBUST AUTOMATIC SPEECH RECOGNITION USING MODULATION SPECTROGRAM FEATURES |
| 1170 | EXPLOITING MAGNITUDE AND PHASE SPECTRAL INFORMATION FOR CONVERTED SPEECH DETECTION |
| 1249 | EYE GAZE FOR UNDERSTANDING CONVERSATIONAL SPEECH |
| 1196 | FORMS2DIALOG: AUTOMATIC DIALOG GENERATION FOR WEB TASKS |
| 1206 | FURTHER INVESTIGATION INTO MULTILINGUAL TRAINING AND ADAPTATION OF STACKED BOTTLE-NECK NEURAL NETWORK STRUCTURE |
| 1109 | GRAMMATICAL ERROR CORRECTION BASED ON LEARNER COMPREHENSION MODEL IN ORAL CONVERSATION |
| 1139 | GRAPH-BASED SEMI-SUPERVISED ACOUSTIC MODELING IN DNN BASED SPEECH RECOGNITION |
| 1078 | IMPROVEMENTS TO SPEAKER ADAPTIVE TRAINING OF DEEP NEURAL NETWORKS |
| 1132 | IMPROVING DEEP NEURAL NETWORKS USING STATE PROJECTION VECTORS OF SUBSPACE GAUSSIAN MIXTURE MODELS AS FEATURES |
| 1122 | IMPROVING SPEAKER RECOGNITION PERFORMANCE IN THE DOMAIN ADAPTATION CHALLENGE USING DEEP NEURAL NETWORKS |
| 1007 | IMPROVING SPEECH-BASED PTSD DETECTION VIA MULTI-VIEW LEARNING |
| 1141 | IMPROVING THE ROBUSTNESS OF EXAMPLE-BASED DIALOG RETRIEVAL USING RECURSIVE NEURAL NETWORK PARAPHRASE IDENTIFICATION |
| 1264 | INCREMENTAL TRANSLATION USING HIERARCHICAL PHRASE-BASED TRANSLATION SYSTEM |
| 1102 | JOINT DECODING OF COMPLEMENTARY UTTERANCES |
| 1070 | JOINT SEMANTIC UTTERANCE CLASSIFICATION AND SLOT FILLING WITH RECURSIVE NEURAL NETWORKS |
| 1145 | KNOWLEDGE-BASED DIALOG STATE TRACKING |
| 1103 | LABEL CORRELATION MIXTURE MODEL FOR MULTI-LABEL TEXT CATEGORIZATION |
| 1106 | LEARNING HIDDEN UNIT CONTRIBUTIONS FOR UNSUPERVISED SPEAKER ADAPTATION OF NEURAL NETWORK ACOUSTIC MODELS |
| 1061 | LEVERAGING FRAME SEMANTICS AND DISTRIBUTIONAL SEMANTICS FOR UNSUPERVISED SEMANTIC SLOT INDUCTION IN SPOKEN DIALOGUE SYSTEMS |
| 1224 | MACHINE LEARNING APPROACHES TO IMPROVING PRONUNCIATION ERROR DETECTION ON AN IMBALANCED CORPUS |
| 1150 | MARGIN-BASED DISCRIMINATIVE PRONUNCIATION MODELING FOR LARGE VOCABULARY MANDARIN SPEECH RECOGNITION |
| 1082 | MARKOVIAN DISCRIMINATIVE MODELING FOR CROSS-DOMAIN DIALOG STATE TRACKING |
| 1079 | MODELING FUNDAMENTAL FREQUENCY DYNAMICS IN HYPOKINETIC DYSARTHRIA |
| 1098 | MULTICHANNEL FEATURE ENHANCEMENT IN DISTRIBUTED MICROPHONE ARRAYS FOR ROBUST DISTANT SPEECH RECOGNITION IN SMART ROOMS |
| 1074 | ONLINE WORD-SPOTTING IN CONTINUOUS SPEECH WITH RECURRENT NEURAL NETWORKS |
| 1060 | ON-THE-FLY USER MODELING FOR COST-SENSITIVE CORRECTION OF SPEECH TRANSCRIPTS |
| 1133 | OPEN-DOMAIN UTTERANCE GENERATION USING PHRASE PAIRS BASED ON DEPENDENCY RELATIONS |
| 1197 | PERSONAL KNOWLEDGE GRAPH POPULATION FROM USER UTTERANCES IN CONVERSATIONAL UNDERSTANDING |
| 1175 | PHONETICS EMBEDDING LEARNING WITH SIDE INFORMATION |
| 1222 | RECOGNITION OF STANCE STRENGTH AND POLARITY IN SPONTANEOUS SPEECH |
| 1193 | RECONSTRUCTION OF ARTICULATORY MEASUREMENTS WITH SMOOTHED LOW-RANK MATRIX COMPLETION |
| 1182 | ROBUST DIALOG STATE TRACKING USING DELEXICALISED RECURRENT NEURAL NETWORKS AND UNSUPERVISED ADAPTATION |
| 1128 | SEMANTIC LANGUAGE MODELS FOR AUTOMATIC SPEECH RECOGNITION |
| 1062 | SEMANTIC PARSER ENHANCEMENT FOR DIALOGUE DOMAIN EXTENSION WITH LITTLE DATA |
| 1018 | SEMI-SUPERVISED DNN TRAINING IN MEETING RECOGNITION |
| 1045 | SPEAKER ADAPTATION OF DEEP NEURAL NETWORKS USING A HIERARCHY OF OUTPUT LAYERS |
| 1219 | SPEAKER DIARIZATION WITH PLDA I-VECTOR SCORING AND UNSUPERVISED CALIBRATION |
| 1087 | SPEAKER-INDEPENDENT DETECTION OF CHILD-DIRECTED SPEECH |
| 1093 | SPOKEN LANGUAGE MISMATCH IN SPEAKER VERIFICATION: AN INVESTIGATION WITH NIST-SRE AND CRSS BI-LING CORPORA |
| 1017 | SPOKEN LANGUAGE UNDERSTANDING USING LONG SHORT-TERM MEMORY NEURAL NETWORKS |
| 1177 | SUBWORD SCHEME FOR KEYWORD SEARCH |
| 1096 | SYLLABLE BASED KEYWORD SEARCH: TRANSDUCING SYLLABLE LATTICES TO WORD LATTICES |
| 1088 | SYSTEM AND KEYWORD DEPENDENT FUSION FOR SPOKEN TERM DETECTION |
| 1149 | TEMPORAL SUPERVISED LEARNING FOR INFERRING A DIALOG POLICY FROM EXAMPLE CONVERSATIONS |
| 1203 | THE INFLUENCE OF AUTOMATIC SPEECH RECOGNITION ACCURACY ON THE PERFORMANCE OF AN AUTOMATED SPEECH ASSESSMENT SYSTEM |
| 1052 | THE THIRD DIALOG STATE TRACKING CHALLENGE |
| 1153 | THE USE OF DISCRIMINATIVE BELIEF TRACKING IN POMDP-BASED DIALOGUE SYSTEMS |
| 1043 | THREE TOBI-BASED MEASURES OF PROSODIC ENTRAINMENT AND THEIR CORRELATIONS WITH SPEAKER ENGAGEMENT |
| 1130 | TIKHONOV REGULARIZATION FOR DEEP NEURAL NETWORK ACOUSTIC MODELING |
| 1238 | TRAINING A STATISTICAL SURFACE REALISER FROM AUTOMATIC SLOT LABELLING |
| 1154 | TRAINING CANDIDATE SELECTION FOR EFFECTIVE REJECTION IN OPEN-SET LANGUAGE IDENTIFICATION |
| 1033 | UNSUPERVISED LEXICAL CLUSTERING OF SPEECH SEGMENTS USING FIXED-DIMENSIONAL ACOUSTIC EMBEDDINGS |
| 1097 | USING LEXICAL, SYNTACTIC AND SEMANTIC FEATURES FOR NON-TERMINAL GRAMMAR RULE INDUCTION IN SPOKEN DIALOGUE SYSTEMS |
| 1227 | UTILIZATION OF UNLABELED DEVELOPMENT DATA FOR SPEAKER VERIFICATION |
| 1067 | UTTERANCE COPY FOR KLATT'S SPEECH SYNTHESIZER USING GENETIC ALGORITHM |
| 1176 | VARIABLE-ACTIVATION AND VARIABLE-INPUT DEEP NEURAL NETWORK FOR ROBUST SPEECH RECOGNITION |
| 1135 | VOCAL TRACT LENGTH NORMALISATION APPROACHES TO DNN-BASED CHILDREN'S AND ADULTS' SPEECH RECOGNITION |
| 1077 | VOICE CONVERSION USING DEEP NEURAL NETWORKS WITH SPEAKER-INDEPENDENT PRE-TRAINING |