Accepted Papers

1006DIFFERENT WORD REPRESENTATIONS AND THEIR COMBINATION FOR PROPER NAME RETRIEVAL FROM DIACHRONIC DOCUMENTS
1008SPARSE NON-NEGATIVE MATRIX LANGUAGE MODELING FOR GEO-ANNOTATED QUERY SESSION DATA
1009TOPIC-SPACE BASED SETUP OF A NEURAL NETWORK FOR THEME IDENTIFICATION OF HIGHLY IMPERFECT TRANSCRIPTIONS
1016SEMI-SUPERVISED SLOT TAGGING IN SPOKEN LANGUAGE UNDERSTANDING USING RECURRENT TRANSDUCTIVE SUPPORT VECTOR MACHINES
1017ADAPTIVE BEAMFORMING AND ADAPTIVE TRAINING OF DNN ACOUSTIC MODELS FOR ENHANCED MULTICHANNEL NOISY SPEECH RECOGNITION
1021TRAINING DATA PSEUDO-SHUFFLING AND DIRECT DECODING FRAMEWORK FOR RECURRENT NEURAL NETWORK BASED ACOUSTIC MODELING
1022INCREMENTAL LSTM-BASED DIALOG STATE TRACKER
1027INCORPORATING USER FEEDBACK TO RE-RANK KEYWORD SEARCH RESULTS
1028COMBINATION OF SYLLABLE BASED N-GRAM SEARCH AND WORD SEARCH FOR SPOKEN TERM DETECTION THROUGH SPOKEN QUERIES AND IV/OOV CLASSIFICATION
1029ON CONSTRUCTING AND ANALYSING AN INTERPRETABLE BRAIN MODEL FOR THE DNN BASED ON HIDDEN ACTIVITY PATTERNS
1032THE 2015 SHEFFIELD SYSTEM FOR TRANSCRIPTION OF MULTI-GENRE BROADCAST MEDIA
1033SPEAKER LOCATION AND MICROPHONE SPACING INVARIANT ACOUSTIC MODELING FROM RAW MULTICHANNEL WAVEFORMS
1038SPOKEN LANGUAGE TRANSLATION GRAPHS RE-DECODING USING AUTOMATIC QUALITY ASSESSMENT
1043A UNIVERSAL MODEL FOR FLEXIBLE ITEM SELECTION IN CONVERSATIONAL DIALOGS
1047INCORPORATING PARAGRAPH EMBEDDINGS AND DENSITY PEAKS CLUSTERING FOR SPOKEN DOCUMENT SUMMARIZATION
1050ANALYSIS OF FACTORS AFFECTING SYSTEM PERFORMANCE IN THE ASPIRE CHALLENGE
1051THE 2015 SHEFFIELD SYSTEM FOR LONGITUDINAL DIARISATION OF BROADCAST MEDIA
1052BOOSTED ACOUSTIC MODEL LEARNING AND HYPOTHESES RESCORING ON THE CHIME3 TASK
1055HYBRID DNN/LATENT STRUCTURED SVM ACOUSTIC MODELS FOR CONTINUOUS SPEECH RECOGNITION
1059UNIFIED ASR SYSTEM USING LGM-BASED SOURCE SEPARATION, NOISE-ROBUST FEATURE EXTRACTION, AND WORD HYPOTHESIS SELECTION
1062DISCRIMINATIVE TRAINING OF CONTEXT-DEPENDENT LANGUAGE MODEL SCALING FACTORS AND INTERPOLATION WEIGHTS
1065AUTOMATIC PROSODY PREDICTION FOR CHINESE SPEECH SYNTHESIS USING BLSTM-RNN AND EMBEDDING FEATURES
1066SPEECH ENHANCEMENT USING BEAMFORMING AND NON NEGATIVE MATRIX FACTORIZATION FOR ROBUST SPEECH RECOGNITION IN THE CHIME-3 CHALLENGE
1068HIGH-PERFORMANCE SWAHILI KEYWORD SEARCH WITH VERY LIMITED LANGUAGE PACK: THE THUEE SYSTEM FOR THE OPENKWS15 EVALUATION
1069SINGLE AND MULTI-CHANNEL APPROACHES FOR DISTANT SPEECH RECOGNITION UNDER NOISY REVERBERANT CONDITIONS: I2R'S SYSTEM DESCRIPTION FOR THE ASPIRE CHALLENGE
1071ACOUSTIC MODEL TRAINING BASED ON NODE-WISE WEIGHT BOUNDARY MODEL INCREASING SPEED OF DISCRETE NEURAL NETWORKS
1075PHONETIC UNIT SELECTION FOR CROSS-LINGUAL QUERY-BY-EXAMPLE SPOKEN TERM DETECTION
1076TWO-STAGE ASGD FRAMEWORK FOR PARALLEL TRAINING OF DNN ACOUSTIC MODELS USING ETHERNET
1081CAMBRIDGE UNIVERSITY TRANSCRIPTION SYSTEMS FOR THE MULTI-GENRE BROADCAST CHALLENGE
1083A COMPARATIVE STUDY OF NEURAL NETWORK MODELS FOR LEXICAL INTENT CLASSIFICATION
1084RNNDROP: A NOVEL DROPOUT FOR RNNS IN ASR
1086AN INFORMATION FUSION APPROACH TO RECOGNIZING MICROPHONE ARRAY SPEECH IN THE CHIME-3 CHALLENGE BASED ON A DEEP LEARNING FRAMEWORK
1088IMPROVING ROBUSTNESS AGAINST REVERBERATION FOR AUTOMATIC SPEECH RECOGNITION
1090MULTI-DOMAIN DIALOGUE SUCCESS CLASSIFIERS FOR POLICY TRAINING
1097SPECTRAL LEARNING WITH NON NEGATIVE PROBABILITIES FOR FINITE STATE AUTOMATON
1103DEEP BI-DIRECTIONAL RECURRENT NETWORKS OVER SPECTRAL WINDOWS
1105NATURALNESS AND RAPPORT IN A PITCH ADAPTIVE LEARNING COMPANION
1107PERSONALIZING UNIVERSAL RECURRENT NEURAL NETWORK LANGUAGE MODEL WITH USER CHARACTERISTIC FEATURES BY SOCIAL NETWORK CROWDSOURCING
1111TIME DELAY DEEP NEURAL NETWORK-BASED UNIVERSAL BACKGROUND MODELS FOR SPEAKER RECOGNITION
1113IMPROVED SYSTEM FUSION FOR KEYWORD SEARCH
1115DEEP MULTIMODAL SEMANTIC EMBEDDINGS FOR SPEECH AND IMAGES
1116AUTOMATION OF SYSTEM BUILDING FOR STATE-OF-THE-ART LARGE VOCABULARY SPEECH RECOGNITION USING EVOLUTION STRATEGY
1117OPEN-DOMAIN PERSONALIZED DIALOG SYSTEM USING USER-INTERESTED TOPICS IN SYSTEM RESPONSES
1120DETECTING ACTIONABLE ITEMS IN MEETINGS BY CONVOLUTIONAL DEEP STRUCTURED SEMANTIC MODELS
1122LEARNING CONTINUOUS REPRESENTATION OF TEXT FOR PHONE DURATION MODELING IN STATISTICAL PARAMETRIC SPEECH SYNTHESIS
1125AN ITERATIVE DEEP LEARNING FRAMEWORK FOR UNSUPERVISED DISCOVERY OF SPEECH FEATURES AND LINGUISTIC UNITS WITH APPLICATIONS ON SPOKEN TERM DETECTION
1129IMPROVING THE INTERPRETABILITY OF DEEP NEURAL NETWORKS WITH STIMULATED LEARNING
1136INVESTIGATING SPARSE DEEP NEURAL NETWORKS FOR SPEECH RECOGNITION
1137A STUDY OF SOCIAL-AFFECTIVE COMMUNICATION: AUTOMATIC PREDICTION OF EMOTION TRIGGERS AND RESPONSES IN TELEVISION TALK SHOWS
1139ADAPTIVE SELECTION FROM MULTIPLE RESPONSE CANDIDATES IN EXAMPLE-BASED DIALOGUE
1140LATENT DIRICHLET ALLOCATION BASED ORGANISATION OF BROADCAST MEDIA ARCHIVES FOR DEEP NEURAL NETWORK ADAPTATION
1141TOWARDS STRUCTURED DEEP NEURAL NETWORK FOR AUTOMATIC SPEECH RECOGNITION
1151OPTIMIZING HUMAN-INTERPRETABLE DIALOG MANAGEMENT POLICY USING GENETIC ALGORITHM
1152LEARNING FACTORIZED FEATURE TRANSFORMS FOR SPEAKER NORMALIZATION
1155IMPROVING DATA SELECTION FOR LOW-RESOURCE STT AND KWS
1162THE DEVELOPMENT OF THE CAMBRIDGE UNIVERSITY ALIGNMENT SYSTEMS FOR THE MULTI-GENRE BROADCAST CHALLENGE
1163THE NTT CHIME-3 SYSTEM: ADVANCES IN SPEECH ENHANCEMENT AND RECOGNITION FOR MOBILE MULTI-MICROPHONE DEVICES
1164BLSTM SUPPORTED GEV BEAMFORMER FRONT-END FOR THE 3RD CHIME CHALLENGE
1172THE NAIST ASR SYSTEM FOR THE 2015 MULTI-GENRE BROADCAST CHALLENGE: ON COMBINATION OF DEEP LEARNING SYSTEMS USING A RANK-SCORE FUNCTION
1178MULTI-CHANNEL SPEECH PROCESSING ARCHITECTURES FOR NOISE ROBUST SPEECH RECOGNITION: 3RD CHIME CHALLENGE RESULTS
1179IMPLEMENTATION OF GENERIC POSITIVE-NEGATIVE TRACKER IN EXTENSIBLE DIALOG SYSTEM
1183INCREMENTAL SENTENCE COMPRESSION USING LSTM RECURRENT NETWORKS
1188SPEAKER DIARISATION AND LONGITUDINAL LINKING IN MULTI-GENRE BROADCAST DATA
1189VARIATIONAL BAYESIAN PLDA FOR SPEAKER DIARIZATION IN THE MGB CHALLENGE
1192MULTIMODAL EMBEDDING FUSION FOR ROBUST SPEAKER ROLE RECOGNITION IN VIDEO BROADCAST
1194THE DIRHA-ENGLISH CORPUS AND RELATED TASKS FOR DISTANT-SPEECH RECOGNITION IN DOMESTIC ENVIRONMENTS
1195STRUCTURED DISCRIMINATIVE MODELS USING DEEP NEURAL-NETWORK FEATURES
1196POLICY COMMITTEE FOR ADAPTATION IN MULTI-DOMAIN SPOKEN DIALOGUE SYSTEMS
1198ROBUST SPEECH RECOGNITION USING BEAMFORMING WITH ADAPTIVE MICROPHONE GAINS AND MULTICHANNEL NOISE REDUCTION
1200UNCERTAINTY ESTIMATION OF DNN CLASSIFIERS
1202A CHIME-3 CHALLENGE SYSTEM: LONG-TERM ACOUSTIC FEATURES FOR NOISE ROBUST AUTOMATIC SPEECH RECOGNITION
1203EESEN: END-TO-END SPEECH RECOGNITION USING DEEP RNN MODELS AND WFST-BASED DECODING
1206STOCHASTIC GRADIENT VARIATIONAL BAYES FOR DEEP LEARNING-BASED ASR
1207TOWARDS UTTERANCE-BASED NEURAL NETWORK ADAPTATION IN ACOUSTIC MODELING
1208THE MERL/SRI SYSTEM FOR THE 3RD CHIME CHALLENGE USING BEAMFORMING, ROBUST FEATURE EXTRACTION, AND ADVANCED SPEECH RECOGNITION
1209INVESTIGATION OF BAC-OFF BASED INTERPOLATION BETWEEN RECURRENT NEURAL NETWORK AND N-GRAM LANGUAGE MODELS
1213LSTM TIME AND FREQUENCY RECURRENCE FOR AUTOMATIC SPEECH RECOGNITION
1214SPEAKER INTONATION ADAPTATION FOR TRANSFORMING TEXT-TO-SPEECH SYNTHESIS SPEAKER IDENTITY
1219DEEP BOTTLENECK FEATURES FOR I-VECTOR BASED TEXT-INDEPENDENT SPEAKER VERIFICATION
1220DISCRIMINATIVE SEGMENTAL CASCADES FOR FEATURE-RICH PHONE RECOGNITION
1225ROBUST SPEECH RECOGNITION IN UNKNOWN REVERBERANT AND NOISY CONDITIONS
1228ROBUST ASR USING NEURAL NETWORK BASED SPEECH ENHANCEMENT AND FEATURE SIMULATION
1229RECENT IMPROVEMENTS TO NEUROCRFS FOR NAMED ENTITY RECOGNITION
1231PHONETICALLY-ORIENTED WORD ERROR ALIGNMENT FOR SPEECH RECOGNITION ERROR ANALYSIS IN SPEECH TRANSLATION
1232A SYSTEM FOR AUTOMATIC ALIGNMENT OF BROADCAST MEDIA CAPTIONS USING WEIGHTED FINITE-STATE TRANSDUCERS
1237CRIM AND LIUM APPROACHES FOR MULTI-GENRE BROADCAST MEDIA TRANSCRIPTION
1238HILBERT SPECTRAL ANALYSIS OF VOWELS USING INTRINSIC MODE FUNCTIONS
1239MULTI-REFERENCE WER FOR EVALUATING ASR FOR LANGUAGES WITH NO ORTHOGRAPHIC RULES
1241ACOUSTIC MODELING WITH NEURAL GRAPH EMBEDDINGS
1242APPLYING DEEP LEARNING TO ANSWER SELECTION: A STUDY AND A BENCHMARK
1243AN I-VECTOR PLDA BASED GENDER IDENTIFICATION APPROACH FOR SEVERELY DISTORTED AND MULTILINGUAL DARPA RATS DATA
1244UTTERANCE CLASSIFICATION IN SPEECH-TO-SPEECH TRANSLATION FOR ZERO-RESOURCE LANGUAGES IN THE HOSPITAL ADMINISTRATION DOMAIN
1245MULTI-TASK JOINT-LEARNING OF DEEP NEURAL NETWORK FOR ROBUST SPEECH RECOGNITION
1250NATURAL LANGUAGE UNDERSTANDING FOR PARTIAL QUERIES
1251TIME-FREQUENCY CONVOLUTIONAL NETWORKS FOR ROBUST SPEECH RECOGNITION
1252MULTITASK LEARNING AND SYSTEM COMBINATION FOR AUTOMATIC SPEECH RECOGNITION
1254USING BIDIRECTIONAL LSTM RECURRENT NEURAL NETWORKS TO LEARN HIGH-LEVEL ABSTRACTIONS OF SEQUENTIAL FEATURES FOR AUTOMATED SCORING OF NON-NATIVE SPONTANEOUS SPEECH
1258SPEAKER ADAPTIVE JOINT TRAINING OF GAUSSIAN MIXTURE MODELS AND BOTTLENECK FEATURES
1263JHU ASPIRE SYSTEM : ROBUST LVCSR WITH TDNNS, I-VECTOR ADAPTATION AND RNN-LMS
1269EXPLOITING SYNCHRONY SPECTRA AND DEEP NEURAL NETWORKS FOR NOISE-ROBUST AUTOMATIC SPEECH RECOGNITION
1270NAME-AWARE LANGUAGE MODEL ADAPTATION AND SPARSE FEATURES FOR STATISTICAL MACHINE TRANSLATION
1273ACOUSTIC MODELLING WITH CD-CTC-SMBR LSTM RNNS
1274MULTILINGUAL REPRESENTATIONS FOR LOW RESOURCE SPEECH RECOGNITION AND KEYWORD SEARCH
1275COMBINING SPECTRAL FEATURE MAPPING AND MULTI-CHANNEL MODEL-BASED SOURCE SEPARATION FOR NOISE-ROBUST AUTOMATIC SPEECH RECOGNITION
1286THE MGB CHALLENGE: EVALUATING MULTI-GENRE BROADCAST MEDIA RECOGNITION
1287THE AUTOMATIC SPEECH RECOGITION IN REVERBERANT ENVIRONMENTS (ASPIRE) CHALLENGE
1288THE THIRD 'CHIME' SPEECH SEPARATION AND RECOGNITION CHALLENGE: DATASET, TASK AND BASELINES.