DNN (Deep Neural Network) & Human Language Technology 2014


See also:

100 Best Deep Belief Network Videos | 100 Best Deep Learning Videos | 100 Best DeepMind Videos | 100 Best GitHub: Deep Learning | Deep Belief Network & Dialog Systems | Deep Learning & Dialog Systems 2014 | Deep Reasoning Systems | DeepDive | DNLP (Deep Natural Language Processing) | DNN (Deep Neural Network) & Human Language Technology 2015 | Skipgram & Deep Learning 2014


Improving deep neural network acoustic models using generalized maxout networks X Zhang, J Trmal, D Povey… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org IMPROVING DEEP NEURAL NETWORK ACOUSTIC MODELS USING GENERALIZED MAXOUT NETWORKS Xiaohui Zhang, Jan Trmal, Daniel Povey, Sanjeev Khudanpur Center for Language and Speech Processing & Human Language Technology Center of Excellence … Cited by 36 Related articles All 7 versions

A novel scheme for speaker recognition using a phonetically-aware deep neural network Y Lei, N Scheffer, L Ferrer… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … [4] GE Dahl, Dong Yu, Li Deng, and A. Acero, “Context- dependent pre-trained deep neural networks for large … and PC Woodland, “Tree-based state tying for high accuracy acoustic modelling,” in HLT ’94 Pro- ceedings of the workshop on Human Language Technology, 1994, pp … Cited by 22 Related articles All 6 versions

Learning phrase representations using rnn encoder-decoder for statistical machine translation K Cho, B van Merrienboer, C Gulcehre… – arXiv preprint arXiv: …, 2014 – arxiv.org … phrases. 1 Introduction Deep neural networks have shown great success in vari- ous applications such as objection recognition (see, eg, (Krizhevsky et al., 2012)) and speech recognition (see, eg, (Dahl et al., 2012)). Furthermore … Cited by 38 Related articles All 10 versions

Joint acoustic modeling of triphones and trigraphemes by multi-task learning deep neural networks for low-resource speech recognition D Chen, B Mak, CC Leung… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … S. Hewavitharana, and T. Schultz, “Thai grapheme-based speech recognition,” in Proceed- ings of the Human Language Technology Conference of the … [11] R. Collobert and J. Weston, “A unified architecture for nat- ural language processing: Deep neural networks with mul … Cited by 6 Related articles All 6 versions

A historical perspective of speech recognition X Huang, J Baker, R Reddy – Communications of the ACM, 2014 – dl.acm.org … 22. Kingsbury, B. et al. Scalable minimum Bayes risk training of deep neural network acoustic models. In Proceedings of Interspeech 2012. 23. … Ward, W. et al. Recent improvements in the CMU SUS. In Proceedings of ARPA Human Language Technology (1994), 213–216. 42. … Cited by 14 Related articles

Automatic speech recognition for under-resourced languages: A survey L Besacier, E Barnard, A Karpov, T Schultz – Speech Communication, 2014 – Elsevier … Artificial Neural Networks (ANN) including single hidden layer NN and multiple hidden layers NN (Deep Neural Networks DNN or Deep Belief Networks DBN) are also used for ASR subtasks such as acoustic modeling (Mohamed et al., 2012 and Seide et al., 2011) and … Cited by 21 Related articles All 6 versions

Application of convolutional neural networks to language identification in noisy conditions Y Lei, L Ferrer, A Lawson… – Proc. Speaker …, 2014 – mc-10136-1356568960.us-west-2. … … modelling,” in HLT ’94 Proceedings of the workshop on Human Language Technology, 1994, pp. 307–312. [14] G. Hinton, L. Deng, D. Yu, GE Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, TN Sainath, and B. Kingsbury, “Deep neural networks for acoustic … Cited by 8 Related articles All 5 versions

Submodular subset selection for large-scale speech training data K Wei, Y Liu, K Kirchhoff, C Bartels… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … particularly good for the deep system, which is encouraging given the recent success deep neural networks have had improving … data subset selection,” in North American Chapter of the Association for Computational Linguistics/Human Language Technology Con- ference … Cited by 7 Related articles All 5 versions

Improving lexical embeddings with semantic knowledge M Yu, M Dredze – Proceedings of the 52nd Annual Meeting of the …, 2014 – aclweb.org … Mark Dredze Human Language Technology Center of Excellence Center for Language and Speech Processing Johns Hopkins University Baltimore, MD 21218 mdredze@cs.jhu … A unified architecture for natural language processing: Deep neural networks with multitask learning … Cited by 5 Related articles All 8 versions

Context dependent state tying for speech recognition using deep neural network acoustic models M Bacchiani, D Rybach – Acoustics, Speech and Signal …, 2014 – ieeexplore.ieee.org … Proc. of Interspeech, 2012. [10] K. Vesely, A. Ghoshal, L.Burget, and D. Povey, “Sequence- discriminative training of deep neural networks,” in Proc. of Interspeech, 2013. … Proc. ARPA Human Language Technology Workshop, 1994. … Cited by 5 Related articles All 5 versions

Deep convolutional neural networks for sentiment analysis of short texts CN dos Santos, M Gatti – … of the 25th International Conference on …, 2014 – aclweb.org … In this work we present a new deep neural network architecture that jointly uses character-level, word- level and sentence-level representations to perform … In Proceedings of the Human Language Technology Conference of the NAACL, pages 1–4, New York City, USA, June. … Cited by 5 Related articles All 3 versions

GMM-free DNN training A Senior, G Heigold, M Bacchiani… – Proc. IEEE Int. Conf. on …, 2014 – bacchiani.net … ICASSP. IEEE, 2012, pp. 4277–4280. [10] N. Jaitly, P. Nguyen, AW Senior, and V. Vanhoucke, “Application of pretrained deep neural networks to large vocabulary speech recognition,” in Proc. Interspeech, 2012. … ARPA Human Language Technology Workshop, 1994. … Cited by 5 Related articles All 4 versions

Recurrent neural networks for word alignment model A Tamura, T Watanabe, E Sumita – Proc. ACL, 2014 – aclweb.org … The most classical approaches are the probabilistic IBM models 1-5 (Brown et al., 1993) and the HMM model (Vogel et al., 1996). Various studies have extended those models. Yang et al. (2013) adapted the Context- Dependent Deep Neural Network for HMM (CD- DNN-HMM … Cited by 3 Related articles All 6 versions

Standalone training of context-dependent deep neural network acoustic models C Zhang, PC Woodland – Acoustics, Speech and Signal …, 2014 – ieeexplore.ieee.org … 7947–7951. [9] KM Knill, MJF Gales, SP Rath, PC Woodland, C. Zhang, and S.-X. Zhang, “Investigation of multilingual deep neural networks for spoken term detection,” in Proc. … Human Language Technology Workshop, Plainsboro, NJ, USA, 1994, pp. 307–312. … Cited by 4 Related articles All 4 versions

Recurrent conditional random field for language understanding K Yao, B Peng, G Zweig, D Yu, X Li… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … Su, G. Li, D. Yu, and F. Seide, “Error back propagation for sequence training of context-dependent deep neural networks for conversational … Shriberg, “Expanding the scope of the ATIS task: The ATIS-3 corpus,” in Proceedings of the workshop on Human Language Technology. … Cited by 6 Related articles All 13 versions

RASR/NN: The RWTH neural network toolkit for speech recognition S Wiesler, A Richard, P Golik… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … 1 Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Aachen, Germany 2 LIMSI CNRS … evaluation of run-time performance and recognition accuracy is performed exemplary with a deep neural network as acoustic … Cited by 2 Related articles

Rescoring N-best lists for Russian speech recognition using factored language models I Kipyatkova, V Verkhodanova, A Karpov – Proc. 4th International …, 2014 – mica.edu.vn … For improvement of acoustical modeling authors used deep neural networks. … 2600–2603, 2006. [5] M. Kurimo, et al., “Unlimited vocabulary speech recognition for agglutinative languages”, in Proceedings of Human Language Technology Conference of the North American … Cited by 2 Related articles All 4 versions

Mean-normalized stochastic gradient for large-scale deep learning S Wiesler, A Richard, R Schluter… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … 1 Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Aachen, Germany 2 LIMSI CNRS, Spoken Language Processing Group, Paris, France ABSTRACT Deep neural networks are typically optimized with stochastic … Cited by 4 Related articles

Multilingual mrasta features for low-resource keyword search and speech recognition systems Z Tuske, D Nolden, R Schluter… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … a Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52056 Aachen, Germany b Spoken Language Processing … [8] G. Heigold et al., “Multilingual acoustic models using dis- tributed deep neural networks,” in Proc. … Cited by 7 Related articles All 4 versions

Combination of FST and CN search in spoken term detection J Chiu, Y Wang, J Trmal, D Povey… – Proc. …, 2014 – mazsola.iit.uni-miskolc.hu … Institute, Carnegie Mellon University, Pittsburgh, PA, USA 2 Center for Language and Speech Processing & Human Language Technology Center of … Each set is conducted on three different decoding systems: a Deep Neural Network (DNN) system, a Bottleneck Feature (BNF … Cited by 4 Related articles All 6 versions

Probabilistic linear discriminant analysis for acoustic modelling L Lu, S Renals – 2014 – ieeexplore.ieee.org … 83, no. 5, pp. 742–772, 1995. [10] G. Hinton, L. Deng, D. Yu, GE Dahl, A.-r. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, TN Sainath, and B. Kingsbury, “Deep neural networks for acoustic … Second Int. Conf. Human Language Technology Research, 2002, pp. … Cited by 4 Related articles All 3 versions

Relation classification via convolutional deep neural network D Zeng, K Liu, S Lai, G Zhou… – Proceedings of …, 2014 – anthology.aclweb.org … In this paper, we exploit a convolutional deep neural network (DNN) to extract lexical and sentence level features for relation … In Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 724–731. … Cited by 4 Related articles All 5 versions

A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling for Handwriting Recognition T Bluche, H Ney, C Kermorvant – Statistical Language and Speech …, 2014 – Springer … Springer International Publishing Switzerland 2014. A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling for Handwriting Recognition. … (3) Human Language Technology and Pattern Recognition, RWTH Aachen … Cited by 1 Related articles All 7 versions

A Deep Neural Network Speaker Verification System Targeting Microphone Speech Y Lei, L Ferrer, M McLaren… – Fifteenth …, 2014 – mc-10136-1356568960.us-west-2. … … 7] G. Dahl, D. Yu, L. Deng, and A. Acero, “Context- dependent pre-trained deep neural networks for large … Odell, and PC Woodland, “Tree-based state tying for high accuracy acoustic modelling,” in HLT ’94 Proceedings of the workshop on Human Language Technology, 1994, pp … Cited by 2 Related articles All 7 versions

Lattice Decoding and Rescoring with Long-Span Neural Network Language Models M Sundermeyer, Z Tüske, R Schlüter… – … Annual Conference of the …, 2014 – 193.6.4.39 … 1 Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Aachen, Germany 2 Spoken Language … 5528–5531 [12] Ar?soy, E., Sainath, TN, Kingsbury, B., and Ramabhadran, B., “Deep Neural Network Language Models … Cited by 2 Related articles All 6 versions

Neural networks leverage corpus-wide information for part-of-speech tagging Y Tsuboi – Proceedings of the 2014 Conference on Empirical …, 2014 – emnlp2014.org … Gulcehre et al., 2014; Zhang et al., 2014). Deep neural networks have been a hot topic in many application areas such as computer vi- 938 Page 2. sion and voice recognition. However, although neural networks show state-of … Cited by 1 Related articles All 6 versions

Labeling unsegmented sequence data with DNN-HMM and its application for speech recognition X Li, X Wu – … Spoken Language Processing (ISCSLP), 2014 9th …, 2014 – ieeexplore.ieee.org … training of context- dependent deep neural network acoustic models,” in Proc. ICAS- SP 2014. [18] Young SJ, Odell JJ, and Woodland PC, “Tree-based s- tate tying for high accuracy acoustic modelling,” Proceedings of the workshop on Human Language Technology. … Cited by 1 Related articles

Probabilistic linear discriminant analysis with bottleneck features for speech recognition L Lu, S Renals – Proc. INTERSPEECH, 2014 – mazsola.iit.uni-miskolc.hu … outcomes in (conversational) speech data col- lection,” in Proceedings of the second international conference on Human Language Technology Research. … F. Seide, G. Li, X. Chen, and D. Yu, “Feature engineering in context-dependent deep neural networks for conversational … Cited by 1 Related articles All 8 versions

Language independent and unsupervised acoustic models for speech recognition and keyword spotting KM Knill, MJF Gales, A Ragni, SP Rath – Proc Inter-Speech, 2014 – 193.6.4.39 … ASRU, 2011. [9] K. Knill et al., “Investigation of multilingual deep neural networks for spoken … [20] S. Young, J. Odell, and P. Woodland, “Tree-based state tying for high accuracy acoustic modelling,” in Proceedings ARPA Work- shop on Human Language Technology, 1994, pp. … Cited by 3 Related articles All 7 versions

Word translation prediction for morphologically rich languages with bilingual neural networks KTABC Monz – staff.fnwi.uva.nl Page 1. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1676–1688, October 25-29, 2014, Doha, Qatar. cO2014 Association for Computational Linguistics Word … Cited by 1 Related articles All 9 versions

Recurrent greedy parsing with neural networks J Legrand, R Collobert – Machine Learning and Knowledge Discovery in …, 2014 – Springer Page 1. Recurrent Greedy Parsing with Neural Networks Joël Legrand 1,2 and Ronan Collobert 1 1 Idiap Research Institute, Rue Marconi 19, Martigny, Switzerland 2 Ecole Polytechnique Fédérale de Lausanne (EPFL) Lausanne … Cited by 1 Related articles All 6 versions

Farewell editorial: keeping up the momentum of innovations L Deng – IEEE/ACM Transactions on Audio, Speech and …, 2014 – dl.acm.org … Many of our editorial team members worked hard to expand the technical topics of the joint T-ASL, resulting in the new category of Human Language Technology. … 20, no. 1, pp. 14–22, Jan. 2012. [6] G. Dahl et al., “Context-dependent pre-trained deep neural networks for large … Cited by 1 Related articles All 3 versions

Event-based text mining for biology and functional genomics S Ananiadou, P Thompson, R Nawaz… – Briefings in …, 2014 – bfg.oxfordjournals.org We use cookies to enhance your experience on our website. By continuing to use our website, you are agreeing to our use of cookies. You can change your cookie settings at any time. Find out more. Skip Navigation. … Cited by 3 Related articles All 4 versions

Featherweight phonetic keyword search for conversational speech K Kintzley, A Jansen… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … US Naval Academy, Annapolis, MD, USA * Human Language Technology Center of Excellence, Center for … For acoustic models, we trained 5-layer deep neural networks to estimate posterior probabilities for 40 phonetic classes, and used them for all subsequent experiments. … Cited by 2 Related articles All 6 versions

Joint Opinion Relation Detection Using One-Class Deep Neural Network L Xu, K Liu, J Zhao – aclweb.org … This paper proposes One-Class Deep Neural Network for joint opinion relation detection in one-class classification scenario, where opinion … In Proceed- ings of the conference on Human Language Technology and Empirical Methods in Natural Language Process- ing, HLT ’05 … Related articles All 4 versions

Advances In Deep Neural Network Approaches To Speaker Recognition M McLaren, Y Lei, L Ferrer – sri.com … Speaker Odyssey, 2014. [10] Y. Lei, L. Ferrer, M. McLaren, and N. Scheffer, “Compara- tive study on the use of senone-based deep neural networks for speaker recognition,” Submitted to IEEE Trans. ASLP, 2014. … Workshop on Human Language Technology, 1994, pp. 307–312. …

Medical Semantic Similarity with a Neural Language Model L De Vine, G Zuccon, B Koopman, L Sitbon… – Proceedings of the 23rd …, 2014 – dl.acm.org … [7] R. Collobert and J. Weston. A unified architecture for natural language processing: Deep neural networks with multitask learning. … In Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 201–208. … Related articles

Product Name Recognition for Informal Text: Exploring Features T He, J Liu – Applied Mechanics and Materials, 2014 – Trans Tech Publ … names from email: applying named entity recognition to informal text,” in Proceedings of the conference on Human Language Technology and Empirical … [17] R. Collobert and J. Weston, “A unified architecture for natural language processing: Deep neural networks with multitask … Related articles All 2 versions

Deep belief network based CRF for spoken language understanding X Yang, J Liu – … (ISCSLP), 2014 9th International Symposium on, 2014 – ieeexplore.ieee.org … Thus, the basic deep neural network architectures also suffer from the label bias problem. … [2] W. Ward and S. Issar, “Recent improvements in the cmu spoken language understanding system,” in Proceedings of the workshop on Human Language Technology. … Related articles

Structural information aware deep semi-supervised recurrent neural network for sentiment analysis W Rong, B Peng, Y Ouyang, C Li, Z Xiong – Frontiers of Computer Science – Springer … unlabelled data. As to the neural network, previously proposed deep neural networks with traditional back propagation algorithm did not get satisfied performance, partially due to not being initial- ized properly [19,54]. Traditionally … Related articles

Improving Speaker Recognition Performance In The Domain Adaptation Challenge Using Deep Neural Networks D Garcia-Romero, X Zhang, A McCree, D Povey – hltcoe.jhu.edu IMPROVING SPEAKER RECOGNITION PERFORMANCE IN THE DOMAIN ADAPTATION CHALLENGE USING DEEP NEURAL NETWORKS Daniel Garcia-Romero, Xiaohui Zhang, Alan McCree, Daniel Povey Human Language Technology Center of Excellence & Center for … Cited by 2 Related articles

Speeding up deep neural networks for speech recognition on ARM Cortex-A series processors A Xing, X Jin, T Li, X Wang, J Pan… – … (ICNC), 2014 10th …, 2014 – ieeexplore.ieee.org … 18. [2] GB Varile and A. Zampolli, Survey of the state of the art in human language technology. Cambridge University Press, 1997, vol. … [6] F. Seide, G. Li, and D. Yu, “Conversational speech transcription using context-dependent deep neural networks.” in Interspeech, 2011, pp. … Related articles

Log-Linear Models, Extensions and Applications A Aravkin, L Deng, G Heigold, T Jebara, D Kanevski… – research.microsoft.com … Future directions are discussed for overcoming this weakness by integrating deep neural networks with deep generative models. … of important machine learning Background methods that have found wide applications, notably in human language technology including speech … Related articles All 4 versions

ICFHR2014 Competition on Handwritten Text Recognition on tranScriptorium Datasets (HTRtS) JA Sánchez, V Romero, AH Toselli, E Vidal – people.sabanciuniv.edu … HTRtS was organised by members of the Pattern Recognition and Human Language Technology re- search center that participate in TRANSCRIPTORIUM … [19] K. Veselý, A. Ghoshal, L. Burget, and D. Povey, “Sequence- discriminative training of deep neural networks,” in Inter … Related articles All 2 versions

Acoustic emotion recognition based on fusion of multiple feature-dependent deep Boltzmann machines K Poon-Feng, DY Huang, M Dong… – … (ISCSLP), 2014 9th …, 2014 – ieeexplore.ieee.org … Agricultural Road Vancouver, BC Canada V6T 1Z1 2 Institute for Infocomm Research/A*STAR Human Language Technology Department 1 … A different approach called Generalized Discriminant Analysis (GerDA) based on Deep Neural Networks (DNNs) is used for learning … Cited by 1 Related articles

Learning a semantic database from unstructured text K Dhandhania – 2014 – dspace.mit.edu Page 1. Learning a semantic database from unstructured text by Keshav Dhandhania Submitted to the Department of Electrical Engineering and Computer Science in Partial Fulfillment of the Requirements for the Degree of … Related articles

Parallel training of Deep Neural Networks with Natural Gradient and Parameter Averaging D Povey, X Zhang, S Khudanpur – arXiv preprint arXiv:1410.7455, 2014 – arxiv.org … Parallel training of Deep Neural Networks with Natural Gradient and Parameter Averaging Daniel Povey? Xiaohui Zhang Sanjeev Khudanpur? Center for Language and Speech Processing, Johns Hopkins University and (?) Human Language Technology Center of Excellence … Cited by 1 Related articles All 6 versions

Decision tree based state tying for speech recognition using DNN derived embeddings X Li, X Wu – … Spoken Language Processing (ISCSLP), 2014 9th …, 2014 – ieeexplore.ieee.org … [11] Zhang C. and Woodland PC, “Standalone training of context- dependent deep neural network acoustic models … SJ, Odell JJ, and Woodland PC, “Tree-based s- tate tying for high accuracy acoustic modelling,” Proceedings of the workshop on Human Language Technology. … Cited by 1 Related articles

Neural network architectures for Prepositional Phrase attachment disambiguation Y Belinkov – 2014 – dspace.mit.edu Page 1. Neural Network Architectures for Prepositional Phrase Attachment Disambiguation by Yonatan Belinkov Submitted to the Department of Electrical Engineering and Computer Science in partial fulfillment of the requirements for the degree of … Related articles All 2 versions

Acoustic modeling for hindi speech recognition in low-resource settings A Dey, W Zhang, P Fung – Audio, Language and Image …, 2014 – ieeexplore.ieee.org … Anik Dey, Weibin Zhang, Pascale Fung Human Language Technology Center Department of Electronic & Computer Engineering The Hong Kong University of Science and Technology adey@connect.ust.hk … A feed-forward network is one form of deep neural network (DNN). … Related articles

Distributed Word Representation Learning for Cross-Lingual Dependency Parsing M Xiao, Y Guo – CoNLL-2014, 2014 – anthology.aclweb.org … We first combine all sentences from both languages to induce real-valued distributed representation of words under a deep neural network architecture, which is expected to capture semantic similari- ties of words not only within the same lan- guage but also across different … Related articles All 8 versions

Data Augmentation, Feature Combination, and Multilingual Neural Networks to Improve ASR and KWS Performance for Low-resource Languages Z Tüske, P Golik, D Nolden… – … Conference of the …, 2014 – mazsola.iit.uni-miskolc.hu … 1 Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52056 Aachen, Germany 2Spoken Language Processing … Because of the great suc- cess of deep neural networks in acoustic modeling and fea- ture extraction … Related articles All 7 versions

Restructuring Output Layers of Deep Neural Networks using Minimum Risk Parameter Clustering Y Kubo, J Suzuki, T Hori… – … Annual Conference of …, 2014 – mazsola.iit.uni-miskolc.hu … the workshop on Human Language Technology, 1994, pp. 307–312. … 20, no. 8, pp. 2252–2264, 2012. [6] J. Xue, J. Li, and Y. Gong, “Restructuring of deep neural network acoustic models with singular value decomposition,” in Proc. In- terspeech, 2013. … Related articles All 4 versions

Grammar as a Foreign Language O Vinyals, L Kaiser, T Koo, S Petrov, I Sutskever… – arXiv preprint arXiv: …, 2014 – arxiv.org … Our results highlight the importance of large datasets when using large deep neural networks that do not contain domain-specific, hand … In Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational … Cited by 4 Related articles All 3 versions

The RWTH English lecture recognition system S Wiesler, K Irie, Z Tuske, R Schluter… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … 1 Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, Aachen, Germany 2´Ecole Centrale … Li, D. Yu, L. Deng, and Y. Gong, “Cross- language knowledge transfer using multilingual deep neural network with shared … Cited by 1 Related articles All 4 versions

Tied Probabilistic Linear Discriminant Analysis for Speech Recognition L Lu, S Renals – arXiv preprint arXiv:1411.0895, 2014 – arxiv.org … We carried out experiments uisng the Switchboard corpus, with both mel frequency cepstral coefficient features and bottleneck feature derived from a deep neural network. Reductions in word error rate were obtained by using … Cited by 1 Related articles

Joint RNN-Based Greedy Parsing and Word Composition J Legrand, R Collobert – arXiv preprint arXiv:1412.7028, 2014 – arxiv.org … Collobert, R. and Weston, J. A unified architecture for natural language processing: Deep neural networks with multitask learning … of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology – Volume 1 … Related articles All 4 versions

Spoken Language Recognition Based on Senone Posteriors L Ferrer, Y Lei, M McLaren… – Fifteenth …, 2014 – mc-10136-1356568960.us-west-2. … … modelling,” in HLT ’94 Proceedings of the workshop on Human Language Technology, 1994, pp. 307–312. [10] G. Hinton, L. Deng, D. Yu, GE Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, TN Sainath, and B. Kingsbury, “Deep neural networks for acoustic … Cited by 3 Related articles All 7 versions

A Systematic Analysis of Automatic Speech Recognition: An Overview T Gulzar, A Singh, DK Rajoriya, N Farooq – 2014 – inpressco.com … Deep neural networks (DNNs) that have multiple hidden layers and are trained using new methods have been shown to smash GMMs on a variety of speech recognition benchmarks, sometimes by a large margin (Heiga Zen et al, 2013). … Related articles

Modeling Compositionality with Multiplicative Recurrent Neural Networks O ?rsoy, C Cardie – arXiv preprint arXiv:1412.6577, 2014 – arxiv.org … Collobert, Ronan and Weston, Jason. A unified architecture for natural language processing: Deep neural networks with multitask learning. … In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, pp. … Related articles All 2 versions

Personalized news recommendation using classified keywords to capture user preference KJ Oh, WJ Lee, CG Lim, HJ Choi – … Technology (ICACT), 2014 …, 2014 – ieeexplore.ieee.org … classify interest keywords more suitable for extracting user preference of news topic using a deep neural network model based … on a daily basis with Columbia’s Newsblaster,” Proceedings of the Second International Conference on Human Language Technology Research,, pp. … Related articles All 5 versions

GMM-free DNN acoustic model training A Senior, G Heigold, M Bacchiani… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … ICASSP. IEEE, 2012, pp. 4277–4280. [10] N. Jaitly, P. Nguyen, AW Senior, and V. Vanhoucke, “Application of pretrained deep neural networks to large vocabulary speech recognition,” in Proc. Interspeech, 2012. … ARPA Human Language Technology Workshop, 1994. … Cited by 1 Related articles All 2 versions

Training State-of-the-Art Portuguese POS Taggers without Handcrafted Features CN dos Santos, B Zadrozny – Computational Processing of the Portuguese …, 2014 – Springer … 5 Conclusions In this work we approach Portuguese POS tagging using a deep neural network architecture that uses a convolutional layer to extract character-level features. … In: Proceedings of the 9th Brazilian Symposium in Information and Human Language Technology, pp. … Related articles All 3 versions

Co-learning of Word Representations and Morpheme Representations S Qiu, Q Cui, J Bian, B Gao, TY Liu – research.microsoft.com … In Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers, pages 1–4, New York City, USA, June. … 2008. A unified architecture for natural language processing: Deep neural networks with multitask learning. In ICML. … Related articles All 8 versions

New Directions for Language Resource Development and Distribution C Cieri, D DiPersio, M Liberman, A Mazzucchi… – ldc.upenn.edu … 3. Remaining Challenges Human Language Technology development has enjoyed rapid gains in performance and coverage over the past decades in large part due to the attention of researchers in numerous related fields and the specific innovations of 1543 Page 6. … Related articles All 2 versions

Recurrent neural network language model adaptation with curriculum learning Y Shi, M Larson, CM Jonker – Computer Speech & Language, 2014 – Elsevier … layer, respectively. The weight matrix between the input layer and hidden layer is estimated by backpropagation-through-time (BPTT) ( Mikolov et al., 2011), which actually unfolds the loop as the deep neural network. In this … Related articles

Chinese Microblog Sentiment Classification Based on Deep Belief Nets with Extended Multi-Modality Features X Sun, C Li, W Xu, F Ren – Data Mining Workshop (ICDMW), …, 2014 – ieeexplore.ieee.org … process. Figure 2. The structure of DBN. In deep learning, DBN is the deep neural network with cascading Boltzmann model. The task of the each RBM layers is used to accomplish abstract representation of input feature. The …

Direct Word Graph Rescoring Using A* Search and RNNLM S Jalalvand, D Falavigna – Fifteenth Annual Conference of the …, 2014 – 193.6.4.39 … Human Language Technology unit, Fondazione Bruno Kessler, via Sommarive 18, Trento, Italy {jalalvand,falavi}@fbk.eu Abstract … [6] Arisoy, E., Sainath, TN, Kingsbury, B., and Ramabhadran, B., “Deep neural network language models”, Proceedings of the NAACL-HLT, pp. … Related articles All 5 versions

Chinese-English mixed text normalization Q Zhang, H Chen, X Huang – Proceedings of the 7th ACM international …, 2014 – dl.acm.org Page 1. Chinese-English Mixed Text Normalization Qi Zhang, Huan Chen, Xuanjing Huang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science, Fudan University 825 Zhangheng Road … Related articles All 3 versions

Factor-based Compositional Embedding Models M Yu, MR Gormley, M Dredze – hltcoe.jhu.edu … Matthew R. Gormley, Mark Dredze Human Language Technology Center of Excellence Center for Language and Speech Processing Johns Hopkins University Baltimore, MD, 21218 {mgormley, mdredze}@cs.jhu … Relation classification via convolu- tional deep neural network. … Cited by 4 Related articles All 5 versions

The NTU-ADSC Systems For Reverberation Challenge 2014 X Xiao, S Zhao, DHH Nguyen, X Zhong, DL Jones… – researchgate.net … Singapore 3School of Computer Engineering, Nanyang Technological University, Singapore 4Department of Human Language Technology, Institute for … Specifically, we train deep neural networks (DNN) to map reverberant spectrogram to the corresponding clean spectrogram … Cited by 2 Related articles All 2 versions

Neural network based feature extraction for speech and image recognition C Plahl – 2014 – darwin.bth.rwth-aachen.de … Page 4. Dipl.-Inform. Christian Plahl Human Language Technology and Pattern Recognition Group RWTH Aachen University plahl@cs.rwth-aachen.de Page 5. … The initialization of the weights of a deep neural network is critical since the op- timization function is non-convex. … Related articles All 6 versions

Transduction Recursive Auto-Associative Memory: Learning Bilingual Compositional Distributed Vector Representations of Inversion Transduction Grammars K Addanki, D Wu – Syntax, Semantics and Structure in Statistical …, 2014 – aclweb.org … Compositional Distributed Vector Representations of Inversion Transduction Grammars Karteek Addanki Dekai Wu HKUST Human Language Technology Center Department … A unified architecture for natural language processing: Deep neural networks with multitask learning. … Related articles All 4 versions

Unsupervised feature learning for sentiment classification of short documents S Albertini, A Zamberletti, I Gallo – Practice and Theory of Opinion Mining and … – jlcl.org … Glorot et al. (2011b) build a deep neural network to learn new representations for the input vectors. … In Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT/EMNLP). … Related articles All 5 versions

Improving Domain-independent Cloud-based Speech Recognition with Domain-dependent Phonetic Post-processing J Twiefel, T Baumann… – Twenty-Eighth …, 2014 – nats-www.informatik.uni-hamburg.de … Cambridge University Press. Jaitly, N.; Nguyen, P.; Senior, AW; and Vanhoucke, V. 2012. Application of pretrained deep neural networks to large vocabulary speech recognition. … In Proceedings of the ARPA Human Language Technology Workshop, 217–221. … Cited by 3 Related articles All 5 versions

An Investigation of Implementation and Performance Analysis of DNN Based Speech Synthesis System Z Chen, K Yu – Signal Processing (ICSP), 2014 12th International …, 2014 – bcmi.sjtu.edu.cn … [13] Q. Yao, F. Y, H. W, and S. Frank K, “On the training aspects of deep neural network (dnn) for … 24] SJ Young, J. Odell, and PC Woodland, “Tree-based state tying for high accuracy acoustic modelling,” in Proceedings of the workshop on Human Language Technology, 1994, pp … Related articles All 2 versions

Librispeech: An ASR Corpus Based On Public Domain Audio Books V Panayotov, G Chen, D Povey, S Khudanpur – danielpovey.com … Center for Language and Speech Processing & Human Language Technology Center of … The acoustic models, referred to as SAT in the tables, are speaker-adapted GMM models [13, 14], and those referred to as DNN, are based on deep neural networks with p-norm non … Cited by 1 Related articles All 3 versions

REVERB Workshop 2014 X Xiao, S Zhao, DHH Nguyen, X Zhong, DL Jones… – reverb2014.dereverberation.com … Singapore 3School of Computer Engineering, Nanyang Technological University, Singapore 4Department of Human Language Technology, Institute for … Specifically, we train deep neural networks (DNN) to map reverberant spectrogram to the corresponding clean spectrogram … Related articles All 2 versions

Text clustering using VSM with feature clusters C Qimin, G Qiao, W Yongliang, W Xianghua – Neural Computing and Applications – Springer … In: Proceedings of the conference on human language technology and empirical methods in natural language processing, pp 755–762. 9. Doucet A … Collobert R, Weston J (2008) A unified architecture for natural language processing: Deep neural networks with multitask learning … Related articles

Training a Korean SRL System with Rich Morphological Features YB Kim, H Chae, B Snyder, YS Kim – 2014 – pages.cs.wisc.edu … 2008. A unified architecture for natural language processing: Deep neural networks with multitask learning. … In Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Lan- guage Processing, pages 371–378. … Cited by 1 Related articles All 8 versions

Learning task-specific bilexical embeddings PS Madhyastha, X Carreras Pérez, A Quattoni – 2014 – upcommons.upc.edu … 2008. A unified architecture for natural language processing: Deep neural networks with multitask learning. … In Proceedings of the workshop on Human Language Technology, HLT ’94, pages 250–255, Stroudsburg, PA, USA. Association for Computational Linguistics. … Cited by 1 Related articles All 6 versions

Language modeling with functional head constraint for code switching speech recognition Y Li, P Fung – Proceedings of the 2014 Conference on Empirical … – aclweb.org … Ying Li and Pascale Fung Human Language Technology Center Department of Electronic and Computer Engineering The Hong Kong University of … Significant progress in speech recognition has been made by using deep neural networks for acoustic modeling and language … Cited by 1 Related articles All 4 versions

Bringing machine learning and compositional semantics together P Liang, C Potts – Annual Reviews of Linguistics (submitted), 0, 2014 – stanford.edu Page 1. Bringing machine learning and compositional semantics together Percy Liang and Christopher Potts Abstract Computational semantics has long been seen as a field divided between logical and statistical approaches … Cited by 5 Related articles All 2 versions

Sentiment Analysis Using Dependency Trees and Named-Entities U Yasavur, J Travieso, C Lisetti, N Rishe – The Twenty-Seventh …, 2014 – cake.fiu.edu … approaches are also fre- quently applied to the sentiment analysis problem, such as linguistically inspired deep neural networks (Socher et … Conference of the North American Chapter of the Association for Com- putational Linguistics on Human Language Technology- Volume 1 … Cited by 1 Related articles All 4 versions

Multiple feature-sets method for dependency parsing X Zhang, D Du, X Liu, W Liang – … Architectures, Algorithms and …, 2014 – ieeexplore.ieee.org … A unified architecture for natural language processing: Deep neural networks with multitask learning. … In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology , pages 134-141. … Related articles All 2 versions

The American Local News Corpus A Irvine, J Langfus, C Callison-Burch – clsp.jhu.edu … author = {Xiaohui Zhang and Jan Trmal and Povey, Daniel and Khudanpur, Sanjeev}, title = {improving deep neural network acoustic models … Abstract. This article describes the resource- and system-building efforts of an eight-week JHU Human Language Technology Center of … Related articles All 6 versions

KIT-Conferences PI Lichtblau – 2014 – isl.anthropomatik.kit.edu … 2013. Sequence-Discriminative Training of Deep Neural Networks, K. Vesely, A. Ghosal, L. Burget, D. Povey. Proceedings … France. Improved Feature Processing for Deep Neural Networks, S. Rath, D. Povey, D. Vesely, J. Cernocky. Proceedings … All 2 versions

Feature compensation using linear combination of speaker and environment dependent correction vectors X Xiao, J Li, ES Chng, H Li – Acoustics, Speech and Signal …, 2014 – ieeexplore.ieee.org … USA 3 School of Computer Engineering, Nanyang Technological University, Singapore 4 Department of Human Language Technology, Institute for … More importantly, the adapted features can be used with any acoustic models, eg deep neural network (DNN) based acoustic … Related articles All 6 versions

Low-rank tensors for scoring dependency structures T Lei, Y Xin, Y Zhang, R Barzilay… – Proceedings of the …, 2014 – people.csail.mit.edu Page 1. Low-Rank Tensors for Scoring Dependency Structures Tao Lei, Yu Xin, Yuan Zhang, Regina Barzilay, and Tommi Jaakkola Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology … Cited by 8 Related articles All 8 versions

Gradient Boosting for Conditional Random Fields T Chen, S Singh, C Guestrin – 2014 – DTIC Document Page 1. ROUTING AND ACTION MEMORANDUM ROUTING TO: (1) Network Sciences Division (Iyer, Purush) Report is available for review (2) Proposal Files Proposal No.: CONTRACT OR GRANT NUMBER: DESCRIPTION OF MATERIAL INSTITUTION: …

Sub-word based language modeling of morphologically rich languages for LVCSR AIED Mousa – 2014 – darwin.bth.rwth-aachen.de … In this work, the use of feed-forward deep neural networks is explored to estimate sub-word based language models. … Hermann Ney, head of the Chair of Human Language Technology and Pattern Recognition, Lehrstuhl für Informatik 6, at the RWTH Aachen University, for his … Related articles All 4 versions

Voice conversion versus speaker verification: an overview Z Wu, H Li – APSIPA Transactions on Signal and Information …, 2014 – Cambridge Univ Press Page 1. SIP (2014), vol. 3, e17, page 1 of 16 © The Authors, 2014. The online version of this article is published within an Open Access environment subject to the conditions of the Creative Commons Attribution-NonCommercial … Cited by 1 Related articles

Articulatory Feature based Continuous Speech Recognition using Probabilistic Lexical Modeling R Rasipuram – 2014 – infoscience.epfl.ch Page 1. TROPE R HCRAESE R PAID I ARTICULATORY FEATURE BASED CONTINUOUS SPEECH RECOGNITION USING PROBABILISTIC LEXICAL MODELING Ramya Rasipuram Mathew Magimai.-Doss Idiap-RR-19-2014 NOVEMBER 2014 … Related articles All 2 versions

Query understanding: applying machine learning algorithms for named entity recognition PO Ashaolu – 2014 – upcommons.upc.edu Page 1. QUERY UNDERSTANDING Applying Machine Learning Algorithms for Named Entity Recognition IT4BI MSc Thesis Author: Paul Ashaolu Official Supervisor: Oscar Romero, PhD Advisor: Toni Cebrian Softonic International SA …

Emotional facial expression transfer based on temporal restricted Boltzmann machines S Liu, DY Huang, W Lin, M Dong, H Li… – Asia-Pacific Signal …, 2014 – ieeexplore.ieee.org … E-mail: liushj09@gmail.com, wslin@ntu.edu.sg Tel: +65-6790 6651 † Human Language Technology Department, 1 Fusionopolis way,#21-01 Connexis (South Tower), Singapore 138632 E-mail: {huang, mhdong, hli, epong}@i2r.a-star.edu.sg Tel: +65-64082639 …

Development and Utility of Automatic Language Processing Technologies. Volume 2 B Ore, J Gwinnup, S Thorn, M Hutt, D Hoeferlin… – 2014 – DTIC Document … This document provides a summary of work completed by SRA International for the Human Language Technology (HLT) Group of 711 HPW/RHXS during the period 08 October 2008 to 31 March 2014 under the Information Operations Cyber Exploitation Research (ICER … Related articles

Development and Evaluation of Semantically Constrained Speech Recognition Architectures S Wermter, J Twiefel, T Baumann – 2014 – informatik.uni-hamburg.de Page 1. Development and Evaluation of Semantically Constrained Speech Recognition Architectures Master Thesis im Arbeitsbereich Knowledge Technology, WTM Prof. Dr. S. Wermter Department Informatik MIN-Fakultät Universität Hamburg … Related articles

Advanced natural language processing for improved prosody in text-to-speech synthesis/GI Schlünz GI Schlünz – 2014 – dspace.nwu.ac.za … I am grateful to be a part of the Human Language Technology Research Group … AAC Augmentative and Alternative Communication DNN Deep Neural Network DP Dynamic Programming DSP Digital Signal Processing DTW Dynamic Time Warping F0 Fundamental Frequency … Related articles

Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis S Khorram, H Sameti… – … Journal on Audio, …, 2014 – asmp.eurasipjournals.com … Bayesian method. Their system was shown to outperform HSMM when the amount of training data is small. Other notable structures used to improve statistical modeling accuracy are deep neural networks (DNNs)[18]. The decision … Cited by 1 Related articles All 4 versions

Foundations and Trends in Signal Processing L Deng, Y Dong – Signal Processing, 2014 – research.microsoft.com Page 1. the essence of knowledge FnT SIG 7:3-4 Deep Learning; Methods and Applications Li Deng and Dong Y u Foundations and Trends® in Signal Processing 7:3-4 Deep Learning Methods and Applications Li Deng and Dong Yu now now Page 2. 7.1. … Cited by 1 Related articles All 8 versions

Capitalising on North American speech resources for the development of a South African English large vocabulary speech recognition system H Kamper, F De Wet, T Hain, T Niesler – Computer Speech & Language, 2014 – Elsevier … b Human Language Technology Competency Area, CSIR Meraka Institute, Pretoria, South Africa; c Department of Computer Science, University of Sheffield, UK. … such as the use of MLP-based features (Qian et al., 2011 and Vu et al., 2012), deep neural networks (Swietojanski et … Related articles All 7 versions

Distinct Acoustic Modeling for Automatic Speech Recognition KO YU-TING – 2014 – cse.ust.hk … 56 4.1 Ranks of the four chosen South African languages in three aspects: their human language technology (HLT) indices, phoneme recogni- tion accuracies, and amount of training data in the … Recently, deep neural network (DNN) [84, 83, 74] is proposed again to model the … Related articles

A family of discriminative manifold learning algorithms and their application to speech recognition VS Tomar, RC Rose – Audio, Speech, and Language …, 2014 – ieeexplore.ieee.org Page 1. Copyright (c) 2013 IEEE. Personal use is permitted. For any other purposes, permission must be obtained from the IEEE by emailing pubs-permissions@ieee.org. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. … Cited by 1 Related articles All 4 versions