Table of Contents

• K-component recurrent neural network language models using curriculum learningYangyang Shi, Martha Larson, Catholijn M. Jonker. 1-6 [doi]
• Learning a subword vocabulary based on unigram likelihoodMatti Varjokallio, Mikko Kurimo, Sami Virpioja. 7-12 [doi]
• Effective pseudo-relevance feedback for language modeling in speech recognitionBerlin Chen, Yi-Wen Chen, Kuan-Yu Chen, Ea-Ee Jan. 13-18 [doi]
• Learning better lexical properties for recurrent OOV wordsLong Qin, Alexander I. Rudnicky. 19-24 [doi]
• Joint training of interpolated exponential n-gram modelsAbhinav Sethy, Stanley F. Chen, Ebru Arisoy, Bhuvana Ramabhadran, Kartik Audhkhasi, Shrikanth Narayanan, Paul Vozila. 25-30 [doi]
• Mixture of mixture n-gram language modelsHasim Sak, Cyril Allauzen, Kaisuke Nakajima, Françoise Beaufays. 31-36 [doi]
• Compact acoustic modeling based on acoustic manifold using a mixture of factor analyzersWen-Lin Zhang, Bi-Cheng Li, Wei-Qiang Zhang. 37-42 [doi]
• A generalized discriminative training framework for system combinationYuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John R. Hershey. 43-48 [doi]
• Acoustic modeling using transform-based phone-cluster adaptive trainingVimal Manohar, Srinivas C. Bhargav, Umesh Srinivasan. 49-54 [doi]
• Speaker adaptation of neural network acoustic models using i-vectorsGeorge Saon, Hagen Soltau, David Nahamoo, Michael Picheny. 55-59 [doi]
• Neighbour selection and adaptation for rapid speaker-dependent ASRUdhyakumar Nallasamy, Mark C. Fuhs, Monika Woszczyna, Florian Metze, Tanja Schultz. 60-65 [doi]
• Efficient nearly error-less LVCSR decoding based on incremental forward and backward passesDavid Nolden, Ralf Schlüter, Hermann Ney. 66-71 [doi]
• Query understanding enhanced by hierarchical parsing structuresJingjing Liu, Panupong Pasupat, Yining Wang, Scott Cyphers, Jim Glass. 72-77 [doi]
• Convolutional neural network based triangular CRF for joint intent detection and slot fillingPuyang Xu, Ruhi Sarikaya. 78-83 [doi]
• Semantic entity detection from multiple ASR hypotheses within the WFST frameworkJan Svec, Pavel Ircing, Lubos Smídl. 84-89 [doi]
• On-line adaptation of semantic models for spoken language understandingAli Orkan Bayer, Giuseppe Riccardi. 90-95 [doi]
• Dysfluent speech detection by image forensics techniquesJuraj Pálfy, Sakhia Darjaa, Jiri Pospichal. 96-101 [doi]
• Barge-in effects in Bayesian dialogue act recognition and simulationHeriberto Cuayáhuitl, Nina Dethlefs, Helen Wright Hastie, Oliver Lemon. 102-107 [doi]
• Expert-based reward shaping and exploration scheme for boosting policy learning of dialogue managementEmmanuel Ferreira, Fabrice Lefevre. 108-113 [doi]
• Dialogue management for leading the conversation in persuasive dialogue systemsTakuya Hiraoka, Yuki Yamauchi, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura. 114-119 [doi]
• Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsingYun-Nung Chen, William Yang Wang, Alexander I. Rudnicky. 120-125 [doi]
• Cross-lingual context sharing and parameter-tying for multi-lingual speech recognitionAanchan Mohan, Richard C. Rose. 126-131 [doi]
• Improved punctuation recovery through combination of multiple speech streamsJoão Miranda, João Paulo da Silva Neto, Alan W. Black. 132-137 [doi]
• Investigation of multilingual deep neural networks for spoken term detectionKate Knill, Mark J. F. Gales, Shakti P. Rath, Philip C. Woodland, Chao Zhang, Shi-Xiong Zhang. 138-143 [doi]
• Language style and domain adaptation for cross-language SLU portingEvgeny A. Stepanov, Ilya Kashkarev, Ali Orkan Bayer, Giuseppe Riccardi, Arindam Ghosh. 144-149 [doi]
• Automatic model complexity control for generalized variable parameter HMMsRongfeng Su, Xunying Liu, Lan Wang. 150-155 [doi]
• Improved cepstral mean and variance normalization using Bayesian frameworkN. Vishnu Prasad, Srinivasan Umesh. 156-161 [doi]
• The second 'CHiME' speech separation and recognition challenge: An overview of challenge systems and outcomesEmmanuel Vincent, Jon Barker, Shinji Watanabe, Jonathan Le Roux, Francesco Nesta, Marco Matassoni. 162-167 [doi]
• Learning state labels for sparse classification of speech with matrix deconvolutionAntti Hurmalainen, Tuomas Virtanen. 168-173 [doi]
• Modified splice and its extension to non-stereo data for noise robust speech recognitionD. S. Pavan Kumar, N. Vishnu Prasad, Vikas Joshi, Srinivasan Umesh. 174-179 [doi]
• A propagation approach to modelling the joint distributions of clean and corrupted speech in the Mel-Cepstral domainRamon Fernadez Astudillo. 180-185 [doi]
• Vector Taylor series based HMM adaptation for generalized cepstrum in noisy environmentSoonho Baek, Hong-Goo Kang. 186-191 [doi]
• The TAO of ATWV: Probing the mysteries of keyword search performanceSteven Wegmann, Arlo Faria, Adam Janin, Korbinian Riedhammer, Nelson Morgan. 192-197 [doi]
• Towards unsupervised semantic retrieval of spoken content with query expansion based on automatically discovered acoustic patternsYun-Chiao Li, Hung-yi Lee, Cheng-Tao Chung, Chun-an Chan, Lin-Shan Lee. 198-203 [doi]
• The IBM keyword search system for the DARPA RATS programLidia Mangu, Hagen Soltau, Hong-Kwang Kuo, George Saon. 204-209 [doi]
• Score normalization and system combination for improved keyword spottingDamianos Karakos, Richard M. Schwartz, Stavros Tsakalidis, Le Zhang, Shivesh Ranjan, Tim Ng, Roger Hsiao, Guruprasad Saikumar, Ivan Bulyko, Long Nguyen, John Makhoul, Frantisek Grézl, Mirko Hannemann, Martin Karafiát, Igor Szöke, Karel Veselý, Lori Lamel, Viet Bac Le. 210-215 [doi]
• Emotion recognition from spontaneous speech using Hidden Markov models with deep belief networksDuc Le, Emily Mower Provost. 216-221 [doi]
• Automatic pronunciation clustering using a World English archive and pronunciation structure analysisH.-P. Shen, Nobuaki Minematsu, T. Makino, S. H. Weinberger, T. Pongkittiphan, C. H. Wu. 222-227 [doi]
• Phonetic and anthropometric conditioning of MSA-KST cognitive impairment characterization systemAlexei V. Ivanov, Shahab Jalalvand, Roberto Gretter, Daniele Falavigna. 228-233 [doi]
• ASR for electro-laryngeal speechAnna Katharina Fuchs, Juan Andres Morales-Cordovilla, Martin Hagmüller. 234-238 [doi]
• Automatic sentiment extraction from YouTube videosLakshmish Kaushik, Abhijeet Sangwan, John H. L. Hansen. 239-244 [doi]
• Acoustic characteristics related to the perceptual pitch in whispered vowelsHideaki Konno, Hideo Kanemitsu, Nobuyuki Takahashi, Mineichi Kudo. 245-249 [doi]
• An SVD-based scheme for MFCC compression in distributed speech recognition systemAzzedine Touazi, Mohamed Debyeche. 250-255 [doi]
• A study of supervised intrinsic spectral analysis for TIMIT phone classificationReza Sahraeian, Dirk Van Compernolle. 256-260 [doi]
• Models of tone for tonal and non-tonal languagesFlorian Metze, Zaid A. W. Sheikh, Alex Waibel, Jonas Gehring, Kevin Kilgour, Quoc-Bao Nguyen, Van Huy Nguyen. 261-266 [doi]
• Semi-supervised training of Deep Neural NetworksKarel Veselý, Mirko Hannemann, Lukas Burget. 267-272 [doi]
• Hybrid speech recognition with Deep Bidirectional LSTMAlex Graves, Navdeep Jaitly, Abdel-rahman Mohamed. 273-278 [doi]
• Improving robustness of deep neural networks via spectral masking for automatic speech recognitionBo Li, Khe Chai Sim. 279-284 [doi]
• Hybrid acoustic models for distant and multichannel large vocabulary speech recognitionPawel Swietojanski, Arnab Ghoshal, Steve Renals. 285-290 [doi]
• Deep maxout neural networks for speech recognitionMeng Cai, Yongzhe Shi, Jia Liu. 291-296 [doi]
• Learning filter banks within a deep neural network frameworkTara N. Sainath, Brian Kingsbury, Abdel-rahman Mohamed, Bhuvana Ramabhadran. 297-302 [doi]
• Accelerating Hessian-free optimization for Deep Neural Networks by implicit preconditioning and samplingTara N. Sainath, Lior Horesh, Brian Kingsbury, Aleksandr Y. Aravkin, Bhuvana Ramabhadran. 303-308 [doi]
• Elastic spectral distortion for low resource speech recognition with deep neural networksNaoyuki Kanda, Ryu Takeda, Yasunari Obuchi. 309-314 [doi]
• Improvements to Deep Convolutional Neural Networks for LVCSRTara N. Sainath, Brian Kingsbury, Abdel-rahman Mohamed, George E. Dahl, George Saon, Hagen Soltau, Tomás Beran, Aleksandr Y. Aravkin, Bhuvana Ramabhadran. 315-320 [doi]
• Combining stochastic average gradient and Hessian-free optimization for sequence training of deep neural networksPierre L. Dognin, Vaibhava Goel. 321-325 [doi]
• Accelerating recurrent neural network training via two stage classes and parallelizationZhiheng Huang, Geoffrey Zweig, Michael Levit, Benoît Dumoulin, Barlas Oguz, Shawn Chang. 326-331 [doi]
• Impact of deep MLP architecture on different acoustic modeling techniques for under-resourced speech recognitionDavid Imseng, Petr Motlícek, Philip N. Garner, Hervé Bourlard. 332-337 [doi]
• Context-dependent modelling of deep neural network using logistic regressionGuangsen Wang, Khe Chai Sim. 338-343 [doi]
• DNN acoustic modeling with modular multi-lingual feature extraction networksJonas Gehring, Quoc-Bao Nguyen, Florian Metze, Alex Waibel. 344-349 [doi]
• Discriminative piecewise linear transformation based on deep learning for noise robust automatic speech recognitionYosuke Kashiwagi, Daisuke Saito, Nobuaki Minematsu, Keikichi Hirose. 350-355 [doi]
• Porting concepts from DNNs back to GMMsKris Demuynck, Fabian Triefenbach. 356-361 [doi]
• Hierarchical neural networks and enhanced class posteriors for social signal classificationRaymond Brueckner, Björn Schuller. 362-367 [doi]
• Large scale deep neural network acoustic modeling with semi-supervised training data for YouTube video transcriptionHank Liao, Erik McDermott, Andrew W. Senior. 368-373 [doi]
• Acoustic data-driven pronunciation lexicon for large vocabulary speech recognitionLiang Lu, Arnab Ghoshal, Steve Renals. 374-379 [doi]
• Acoustic unit discovery and pronunciation generation from a grapheme-based lexiconWilliam Hartmann, Anindya Roy, Lori Lamel, Jean-Luc Gauvain. 380-385 [doi]
• A hierarchical system for word discovery exploiting DTW-based initializationOliver Walter, Timo Korthals, Reinhold Haeb-Umbach, Bhiksha Raj. 386-391 [doi]
• NMF-based keyword learning from scarce dataBart Ons, Jort F. Gemmeke, Hugo Van Hamme. 392-397 [doi]
• Deep maxout networks for low-resource speech recognitionYajie Miao, Florian Metze, Shourabh Rawat. 398-403 [doi]
• Combination of data borrowing strategies for low-resource LVCSRYanmin Qian, Kai Yu, Jia Liu. 404-409 [doi]
• Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settingsKeith Levin, Katharine Henry, Aren Jansen, Karen Livescu. 410-415 [doi]
• Using proxies for OOV keywords in the keyword search taskGuoguo Chen, Oguz Yilmaz, Jan Trmal, Daniel Povey, Sanjeev Khudanpur. 416-421 [doi]
• Search results based N-best hypothesis rescoring with maximum entropy classificationFuchun Peng, Scott Roy, Ben Shahshahani, Françoise Beaufays. 422-427 [doi]
• Using web text to improve keyword spotting in speechAnkur Gandhe, Long Qin, Florian Metze, Alexander I. Rudnicky, Ian R. Lane, Matthias Eck. 428-433 [doi]
• Multi-stream temporally varying weight regression for cross-lingual speech recognitionShilin Liu, Khe Chai Sim. 434-439 [doi]
• Discriminative semi-supervised training for keyword search in low resource languagesRoger Hsiao, Tim Ng, Frantisek Grézl, Damianos Karakos, Stavros Tsakalidis, Long Nguyen, Richard M. Schwartz. 440-445 [doi]
• Probabilistic lexical modeling and unsupervised training for zero-resourced ASRRamya Rasipuram, Marzieh Razavi, Mathew Magimai-Doss. 446-451 [doi]
• Lightly supervised automatic subtitling of weather forecastsJoris Driesen, Steve Renals. 452-457 [doi]
• Unsupervised word segmentation from noisy inputJahn Heymann, Oliver Walter, Reinhold Haeb-Umbach, Bhiksha Raj. 458-463 [doi]
• An empirical study of confusion modeling in keyword search for low resource languagesMurat Saraclar, Abhinav Sethy, Bhuvana Ramabhadran, Lidia Mangu, Jia Cui, Xiaodong Cui, Brian Kingsbury, Jonathan Mamou. 464-469 [doi]
• Semi-supervised bootstrapping approach for neural network feature extractor trainingFrantisek Grézl, Martin Karafiát. 470-475 [doi]