Table of Contents

• Semantic language models for Automatic Speech RecognitionAli Orkan Bayer, Giuseppe Riccardi. 7-12 [doi]
• Context-based recognition network adaptation for improving on-line ASR in Air Traffic ControlAnna Schmidt, Youssef Oualil, Oliver Ohneiser, Matthias Kleinert, Marc Schulder, Arif Khan, Hartmut Helmke, Dietrich Klakow. 13-18 [doi]
• Voice conversion using deep neural networks with speaker-independent pre-trainingSeyed Hamidreza Mohammadi, Alexander Kain. 19-23 [doi]
• Efficient multi-lingual unsupervised acoustic model training under mismatch conditionsMasahiro Saiko, Hitoshi Yamamoto, Ryosuke Isotani, Chiori Hori. 24-29 [doi]
• Acquisition of ordinal words using weakly supervised NMFVincent Renkens, Steven Janssens, Bart Ons, Jort F. Gemmeke, Hugo Van Hamme. 30-35 [doi]
• A data-driven phoneme mapping technique using interpolation vectors of phone-cluster adaptive trainingBasil Abraham, Neethu Mariam Joy, Navneeth K. S. Umesh. 36-41 [doi]
• Document-based Dirichlet class language model for speech recognition using document-based n-gram eventsMd. Akmal Haidar, Douglas D. O'Shaughnessy. 42-47 [doi]
• Further investigation into multilingual training and adaptation of stacked bottle-neck neural network structureFrantisek Grézl, Ekaterina Egorova, Martin Karafiát. 48-53 [doi]
• Reconstruction of articulatory measurements with smoothed low-rank matrix completionWeiran Wang, Raman Arora, Karen Livescu. 54-59 [doi]
• Open-domain utterance generation using phrase pairs based on dependency relationsHiroaki Sugiyama, Toyomi Meguro, Ryuichiro Higashinaka, Yasuhiro Minami. 60-65 [doi]
• Bilingual Recurrent Neural Networks for improved statistical machine translationBing Zhao, Yik-Cheung Tam. 66-70 [doi]
• Incremental translation using hierarchichal phrase-based translation systemMaryam Siahbani, Ramtin Mehdizadeh Seraj, Baskaran Sankaran, Anoop Sarkar. 71-76 [doi]
• Domain invariant speech features using a new divergence measureAlan Wisler, Visar Berisha, Julie Liss, Andreas Spanias. 77-82 [doi]
• Label correlation mixture model for multi-label text categorizationZhiyang He, Ji Wu, Ping Lv. 83-88 [doi]
• Utterance copy for Klatt's speech synthesizer using genetic algorithmJose Sousa, Fabiola Araujo, Aldebaro Klautau. 89-94 [doi]
• A methodology for using crowdsourced data to measure uncertainty in natural speechLara Martin, Matthew Stone, Florian Metze, Jack Mostow. 95-99 [doi]
• Unsupervised lexical clustering of speech segments using fixed-dimensional acoustic embeddingsHerman Kamper, Aren Jansen, Simon King, Sharon Goldwater. 100-105 [doi]
• Phonetics embedding learning with side informationGabriel Synnaeve, Thomas Schatz, Emmanuel Dupoux. 106-111 [doi]
• Training a statistical surface realiser from automatic slot labellingHeriberto Cuayáhuitl, Nina Dethlefs, Helen F. Hastie, Xingkun Liu. 112-117 [doi]
• Background-tracking acoustic features for genre identification of broadcast showsOscar Saz, Mortaza Doulaty, Thomas Hain. 118-123 [doi]
• Deep Order Statistic NetworksSteven J. Rennie, Vaibhava Goel, Samuel Thomas. 124-128 [doi]
• Improving deep neural networks using state projection vectors of subspace Gaussian mixture model as featuresMurali Karthick B, S. Umesh. 129-134 [doi]
• Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognitionRomain Serizel, Diego Giuliani. 135-140 [doi]
• Semi-supervised DNN training in meeting recognitionPengyuan Zhang, Yulan Liu, Thomas Hain. 141-146 [doi]
• Tikhonov regularization for deep neural network acoustic modelingJen-Tzung Chien, Tsai-Wei Lu. 147-152 [doi]
• Speaker adaptation of deep neural networks using a hierarchy of output layersRyan Price, Ken-ichi Iso, Koichi Shinoda. 153-158 [doi]
• Annealed dropout training of deep networksSteven J. Rennie, Vaibhava Goel, Samuel Thomas. 159-164 [doi]
• Improvements to speaker adaptive training of deep neural networksYajie Miao, Lu Jiang, Hao Zhang, Florian Metze. 165-170 [doi]
• Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic modelsPawel Swietojanski, Steve Renals. 171-176 [doi]
• Graph-based semi-supervised acoustic modeling in DNN-based speech recognitionYuzong Liu, Katrin Kirchhoff. 177-182 [doi]
• A distributed architecture for fast SGD sequence discriminative training of DNN acoustic modelsGeorge Saon. 183-188 [doi]
• Spoken language understanding using long short-term memory neural networksKaisheng Yao, Baolin Peng, Yu Zhang, Dong Yu, Geoffrey Zweig, Yangyang Shi. 189-194 [doi]
• A discriminative model based entity dictionary weighting approach for spoken language understandingXiaohu Liu, Ruhi Sarikaya. 195-199 [doi]
• Entity ranking for descriptive queriesKai Hong, Pengjun Pei, Ye-Yi Wang, Dilek Hakkani-Tür. 200-205 [doi]
• Bayesian recurrent neural network language modelJen-Tzung Chien, Yuan-Chu Ku. 206-211 [doi]
• Joint decoding of complementary utterancesMickael Rouvier, Benoît Favre, Frédéric Béchet. 212-217 [doi]
• Author-topic based representation of call-center conversationsMohamed Morchid, Richard Dufour, Mohamed Bouallegue, Georges Linarès. 218-223 [doi]
• Personal knowledge graph population from user utterances in conversational understandingXiang Li, Gökhan Tür, Dilek Hakkani-Tür, Qi Li. 224-229 [doi]
• Effective data-driven feature learning for detecting name errors in automatic speech recognitionJi He, Alex Marin, Mari Ostendorf. 230-235 [doi]
• Recognition of stance strength and polarity in spontaneous speechGina-Anne Levow, Valerie Freeman, Alena Hrynkevich, Mari Ostendorf, Richard A. Wright, Julian Chan, Yi Luan, Trang tran. 236-241 [doi]
• Deriving local relational surface forms from dependency-based entity embeddings for unsupervised spoken language understandingYun-Nung Chen, Dilek Hakkani-Tür, Gökhan Tür. 242-247 [doi]
• Dysarthric vocal interfaces with minimal training dataJort F. Gemmeke, Siddharth Sehgal, Stuart Cunningham, Hugo Van Hamme. 248-253 [doi]
• Automatic selection of speakers for improved acoustic modelling: recognition of disordered speech with sparse dataHeidi Christensen, I. Casanueva, Stuart Cunningham, Phil D. Green, Thomas Hain. 254-259 [doi]
• Improving speech-based PTSD detection via multi-view learningXiaodan Zhuang, Viktor Rozgic, Michael Crystal, Brian Marx. 260-265 [doi]
• Computational analysis of trajectories of linguistic development in autismEmily Prud'hommeaux, Eric Morley, Masoud Rouhizadeh, Laura Silverman, Jan P. H. van Santen, Brian Roark, Richard Sproat, Sarah Kauper, Rachel DeLaHunta. 266-271 [doi]
• Modeling fundamental frequency dynamics in hypokinetic dysarthriaMahsa Sadat Elyasi Langarani, Jan P. H. van Santen. 272-276 [doi]
• Adolescent suicidal risk assessment in clinician-patient interaction: A study of verbal and acoustic behaviorsVerena Venek, Stefan Scherer, Louis-Philippe Morency, Albert A. Rizzo, John Pestian. 277-282 [doi]
• Grammatical error correction based on learner comprehension model in oral conversationKyusong Lee, Seonghan Ryu, Hongsuck Seo, Seokhwan Kim, Gary Geunbae Lee. 283-287 [doi]
• A comparison of acoustic-prosodic entrainment in face-to-face and remote collaborative learning dialoguesNichola Lubold, Heather Pon-Barry. 288-293 [doi]
• The influence of automatic speech recognition accuracy on the performance of an automated speech assessment systemJidong Tao, Keelan Evanini, Xinhao Wang. 294-299 [doi]
• Machine learning approaches to improving pronunciation error detection on an imbalanced corpusXuesong Yang, Anastassia Loukina, Keelan Evanini. 300-305 [doi]
• Improving the robustness of example-based dialog retrieval using recursive neural network paraphrase identificationLasguido Nio, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura. 306-311 [doi]
• Temporal supervised learning for inferring a dialog policy from example conversationsLihong Li, He He, Jason D. Williams. 312-317 [doi]
• A discriminative sequence model for dialog state tracking using user goal change detectionYi Ma, Eric Fosler-Lussier. 318-323 [doi]
• The third Dialog State Tracking ChallengeMatthew Henderson, Blaise Thomson, Jason D. Williams. 324-329 [doi]
• A generalized rule based tracker for dialogue state trackingKai Sun, Lu Chen, Su Zhu, Kai Yu. 330-335 [doi]
• Semantic parser enhancement for dialogue domain extension with little dataSu Zhu, Lu Chen, Kai Sun, Da Zheng, Kai Yu. 336-341 [doi]
• Markovian discriminative modeling for cross-domain dialog state trackingHang Ren, Weiqun Xu, Yonghong Yan 0002. 342-347 [doi]
• Knowledge-based Dialog State TrackingRudolf Kadlec, Miroslav Vodolan, Jindrich Libovicky, Jan Macek, Jan Kleindienst. 348-353 [doi]
• The use of discriminative belief tracking in POMDP-based dialogue systemsDongHo Kim, Matthew Henderson, Milica Gasic, Pirros Tsiakoulis, Steve J. Young. 354-359 [doi]
• Robust dialog state tracking using delexicalised recurrent neural networks and unsupervised adaptationMatthew Henderson, Blaise Thomson, Steve J. Young. 360-365 [doi]
• Speaker-independent detection of child-directed speechSebastian Schuster, Stephanie Pancoast, Milind Ganjoo, Michael C. Frank, Dan Jurafsky. 366-371 [doi]
• Spoken language mismatch in speaker verification: An investigation with NIST-SRE and CRSS Bi-Ling corporaAbhinav Misra, John H. L. Hansen. 372-377 [doi]
• Improving speaker recognition performance in the domain adaptation challenge using deep neural networksDaniel Garcia-Romero, Xiaohui Zhang, Alan McCree, Daniel Povey. 378-383 [doi]
• Training candidate selection for effective rejection in open-set language identificationQian Zhang, John H. L. Hansen. 384-389 [doi]
• Constrained speaker diarization of TV series based on visual patternsXavier Bost, Georges Linarès. 390-395 [doi]
• Exploiting magnitude and phase spectral information for converted speech detectionMaria Joana Correia, Alberto Abad, Isabel Trancoso. 396-401 [doi]
• Artificial neural network features for speaker diarizationSree Harsha Yella, Andreas Stolcke, Malcolm Slaney. 402-406 [doi]
• Discrimination between singing and speech in real-world audioBrian Thompson. 407-412 [doi]
• Speaker diarization with plda i-vector scoring and unsupervised calibrationGregory Sell, Daniel Garcia-Romero. 413-417 [doi]
• Utilization of unlabeled development data for speaker verificationGang Liu, Chengzhu Yu, Navid Shokouhi, Abhinav Misra, Hua Xing, John H. L. Hansen. 418-423 [doi]
• EM-based phoneme confusion matrix generation for low-resource spoken term detectionDi Xu, Yun Wang, Florian Metze. 424-429 [doi]
• System and keyword dependent fusion for spoken term detectionVan Tung Pham, Nancy F. Chen, Sunil Sivadas, Haihua Xu, I-Fan Chen, Chongjia Ni, Engsiong Chng, Haizhou Li. 430-435 [doi]
• Effective combination of heterogeneous subword-based spoken term detection systemsShi-wook Lee, Kazuyo Tanaka, Yoshiaki Itoh 0001. 436-441 [doi]
• Combining local and broad topic context to improve term detectionJonathan Wintrode, Sanjeev Khudanpur. 442-447 [doi]
• A multimodal stroke-based predictive input for efficient Chinese text entry on mobile devicesKhe Chai Sim. 448-453 [doi]
• An efficient error correction interface for speech recognition on mobile touchscreen devicesYuan Liang, Koji Iwano, Koichi Shinoda. 454-459 [doi]
• On-the-fly user modeling for cost-sensitive correction of speech transcriptsMatthias Sperber, Graham Neubig, Satoshi Nakamura, Alex Waibel. 460-465 [doi]
• Emotion recognition on Indonesian television talk showsNurul Lubis, Dessi Puji Lestari, Ayu Purwarianti, Sakriani Sakti, Satoshi Nakamura. 466-471 [doi]
• Evaluation of syllable rate estimation in expressive speech and its contribution to emotion recognitionMohammed Abdel-Wahab, Carlos Busso. 472-477 [doi]
• Classification of lexical stress patterns using deep neural network architectureMostafa Ali Shahin, Beena Ahmed, Kirrie J. Ballard. 478-482 [doi]
• Subword scheme for keyword searchZhipeng Chen, Teng Zhang, Ji Wu. 483-488 [doi]
• Syllable based keyword search: Transducing syllable lattices to word latticesHang Su, James Hieronymus, Yanzhang He, Eric Fosler-Lussier, Steven Wegmann. 489-494 [doi]
• A word-level token-passing decoder for subword n-gram LVCSRMatti Varjokallio, Mikko Kurimo. 495-500 [doi]
• But ASR system for BABEL Surprise evaluation 2014Martin Karafiát, Karel Veselý, Igor Szöke, Lukás Burget, Frantisek Grézl, Mirko Hannemann, Jan Cernocký. 501-506 [doi]
• Multichannel feature enhancement in distributed microphone arrays for robust distant speech recognition in smart roomsSeyedmahdad Mirsamadi, John H. L. Hansen. 507-512 [doi]
• A sparsity based preprocessing for noise robust speech recognitionChristos Koniaris, Saikat Chatterjee. 513-518 [doi]
• Exemplar-based noise robust automatic speech recognition using modulation spectrogram featuresDeepak Baby, Tuomas Virtanen, Jort F. Gemmeke, Tom Barker, Hugo Van Hamme. 519-524 [doi]
• A complete KALDI recipe for building Arabic speech recognition systemsAhmed M. Ali, Yifan Zhang, Patrick Cardinal, Najim Dahak, Stephan Vogel, James R. Glass. 525-529 [doi]
• A keyword search system using open source softwareJan Trmal, Guoguo Chen, Daniel Povey, Sanjeev Khudanpur, Pegah Ghahremani, Xiaohui Zhang, Vimal Manohar, Chunxi Liu, Aren Jansen, Dietrich Klakow, David Yarowsky, Florian Metze. 530-535 [doi]
• Online word-spotting in continuous speech with recurrent neural networksPallavi Baljekar, Jill Fain Lehman, Rita Singh. 536-541 [doi]
• Variable-activation and variable-input deep neural network for robust speech recognitionRui Zhao, Jinyu Li, Yifan Gong. 542-547 [doi]
• Deep convolutional nets and robust features for reverberation-robust speech recognitionVikramjit Mitra, Wen Wang, Horacio Franco. 548-553 [doi]
• Joint semantic utterance classification and slot filling with recursive neural networksDaniel Guo, Gökhan Tür, Wen-tau Yih, Geoffrey Zweig. 554-559 [doi]
• Data collection and language understanding of food descriptionsMandy Korpusik, Nicole Schmidt, Jennifer Drexler, Scott Cyphers, James R. Glass. 560-565 [doi]
• Distributed open-domain conversational understanding framework with domain independent extractorsQi Li, Gökhan Tür, Dilek Hakkani-Tür, Xiang Li, Tim Paek, Asela Gunawardana, Chris Quirk. 566-571 [doi]
• Eye gaze for understanding conversational speechAnna Prokofieva, Dilek Hakkani-Tür, Malcolm Slaney. 572-577 [doi]
• Three ToBI-based measures of prosodic entrainment and their correlations with speaker engagementAgustín Gravano, Stefan Benus, Rivka Levitan, Julia Hirschberg. 578-583 [doi]
• Leveraging frame semantics and distributional semantics for unsupervised semantic slot induction in spoken dialogue systemsYun-Nung Chen, William Yang Wang, Alexander I. Rudnicky. 584-589 [doi]
• Dynamically supporting unexplored domains in conversational interactions by enriching semantics with neural word embeddingsYun-Nung Chen, Alexander I. Rudnicky. 590-595 [doi]
• Using lexical, syntactic and semantic features for non-terminal grammar rule induction in Spoken Dialogue SystemsGeorgia Athanasopoulou, Ioannis Klasinas, Spiros Georgiladakis, Elias Iosif, Alexandros Potamianos. 596-601 [doi]
• An end-to-end dialog system for TV program discoveryDeepak Ramachandran, Peter Z. Yeh, William Jarrold, Benjamin Douglas, Adwait Ratnaparkhi, Ronald Provine, Jeremy Mendel, Adam Emfield. 602-607 [doi]
• Forms2Dialog: Automatic dialog generation for Web tasksNobal B. Niraula, Amanda Stent, Hyuckchul Jung, Giuseppe Di Fabbrizio, I. Dan Melamed, Vasile Rus. 608-613 [doi]