Autoencoder & Dialog Systems 2016


Notes:

An autoencoder is a artificial neural network used for learning a compressed representation for feature extraction.

Resources:

  • dblp.org/db/conf/nldb .. annual conference on applications of natural language to data bases
  • kueri.me .. search-box interface to allow users to navigate, explore, and present data

Wikipedia:

See also:

100 Best Convolutional Neural Network Videos100 Best GitHub: Deep Learning | CNN (Convolutional Neural Network) & Dialog Systems 2016Neural Network & Dialog Systems 2016


Squeezing bottlenecks: exploring the limits of autoencoder semantic representation capabilities
P Gupta, RE Banchs, P Rosso – Neurocomputing, 2016 – Elsevier
… In a neural network based implementation of the autoencoder, the visible layer corresponds to the input x and the hidden layer corresponds to y. There are two variants of autoencoders: (i) with a single hidden layer, and (ii) with multiple hidden layers. …

Neural Emoji Recommendation in Dialogue Systems
R Xie, Z Liu, R Yan, M Sun – arXiv preprint arXiv:1612.04609, 2016 – arxiv.org
… Page 7. We will explore more flexible emoji recommendation meth- ods in dialogue systems with emoji positions and coherence into … A hierarchical neural autoencoder for paragraphs and documents … Semi-supervised recursive autoencoders for predict- ing sentiment distributions …

Two are Better than One: An Ensemble of Retrieval-and Generation-Based Dialog Systems
Y Song, R Yan, X Li, D Zhao, M Zhang – arXiv preprint arXiv:1610.07149, 2016 – arxiv.org
… [9] Jiwei Li, Thang Luong, and Dan Jurafsky. A hierarchical neural autoencoder for paragraphs and docu- ments. … How NOT to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation. In EMNLP (to appear), 2016. …

Root Cause Analysis of Miscommunication Hotspots in Spoken Dialogue Systems.
S Georgiladakis, G Athanasopoulou… – …, 2016 – pdfs.semanticscholar.org
… 1, pp. 155–175, 2004. [14] R. Meena, “Data-driven methods for spoken dialogue systems: Applications in … 207–218, 2014. [16] R. Socher, EH Huang, J. Pennin, CD Manning, and AY Ng, “Dynamic pooling and unfolding recursive autoencoders for paraphrase detection,” in Proc. …

Using phone features to improve dialogue state tracking generalisation to unseen states
I Casanueva, T Hain, M Nicolao… – Proceeding of SIGDIAL …, 2016 – eprints.whiterose.ac.uk
… 1In a slot based dialogue system the dialogue states are defined as the set of possible value combinations for each slot. … For the task of gen- erating dense representations of phone sequences, the seq2seq model is trained in a similar way to auto-encoders (Vincent et al., 2008 …

A Unified Knowledge Representation System for Robot Learning and Dialogue
N Shukla – 2016 – search.proquest.com
… The uents are typically hand-chosen, but we suggest automatically generating various abstractions of uents by varying the dimensionality of autoencoders. … Collaborative activities and multi-tasking in dialogue systems: Towards natural dialogue with robots. TAL. …

Neural Network Approaches to Dialog Response Retrieval and Generation
L Nio, S Sakti, G Neubig, K Yoshino… – … on Information and …, 2016 – search.ieice.org
… incomprehensible to the user [9]. There have been a number of works on response gener- ation for data-driven dialog systems. … In the fol- lowing sections we describe: (1) word representations, the input to the RAE, (2) recursive autoencoders, and (3 … 4.2 Recursive Autoencoder …

Semi-Supervised Learning with Sparse Autoencoders in Automatic Speech Recognition
AK Dhaka – 2016 – diva-portal.org
… If the hidden layer of the auto-encoder has a lower dimensionality than the input, the model will perform non-linear dimensionality … 2.5.2 Sparse Autoencoders Historically, the first application of autoencoder was for reducing dimensions of the in- put data, hence the name. …

Multi-modal variational encoder-decoders
IV Serban, II Ororbia, G Alexander, J Pineau… – arXiv preprint arXiv …, 2016 – arxiv.org
… of powerful directed graphical models with continuous latent variables, such as variational autoencoders. … With the development of the variational autoencoding framework (Kingma & Welling … Simultaneously with this work, the variational autoencoder framework was proposed by …

Learning to respond with deep neural networks for retrieval-based human-computer conversation system
R Yan, Y Song, H Wu – Proceedings of the 39th International ACM SIGIR …, 2016 – dl.acm.org
Page 1. Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System Rui Yan Baidu Inc. No. 10, Xibeiwang East Road, Beijing 100193, China yanrui02@baidu.com Yiping Song Baidu Inc. No. …

A latent variable recurrent neural network for discourse relation language models
Y Ji, G Haffari, J Eisenstein – arXiv preprint arXiv:1603.01913, 2016 – arxiv.org
… which was the 2015 CoNLL shared task (Xue et al., 2015); and dialog act clas- sification, which characterizes the structure of in- terpersonal communication in the Switchboard cor- pus (Stolcke et al., 2000), and is a key component of contemporary dialog systems (Williams and …

Learning distributed representations of sentences from unlabelled data
F Hill, K Cho, A Korhonen – arXiv preprint arXiv:1602.03483, 2016 – arxiv.org
… Sutskever et al., 2014), image captioning (Mao et al., 2015) and dialogue systems (Serban et … avoid this restriction, we experiment with a representation-learning objective based on denoising autoencoders (DAEs … We call this model the Sequential Denoising Autoencoder (SDAE …

Hidden Softmax Sequence Model for Dialogue Structure Analysis.
Z He, X Liu, P Lv, J Wu – ACL (1), 2016 – aclweb.org
… The technology provides essential clues for solving real-world problems, such as pro- ducing dialogue summaries (Murray et al., 2006; Liu et al., 2010), controlling conversational agents (Wilks, 2006), and designing interactive dialogue systems (Young, 2006; Allen et al., 2007 …

Deep neural network based feature extraction using convex-nonnegative matrix factorization for low-resource speech recognition
C Qin, L Zhang – Information Technology, Networking …, 2016 – ieeexplore.ieee.org
… Sainath et al. [6] used auto- encoder neural network to reduce feature dimensions. … [5] J. Gehring, Y. Miao, et al., “Extracting deep bottleneck features using stacked auto-encoders,” in Proc. … [6] TN Sainath, B. Kingsbury, and B. Ramabhadran, “Autoencoder bottleneck features …

Speech and Computer: 18th International Conference, SPECOM 2016, Budapest, Hungary, August 23-27, 2016, Proceedings
A Ronzhin, R Potapova, G Németh – 2016 – books.google.com
… 140 András Beke and György Szaszák Backchanneling via Twitter Data for Conversational Dialogue Systems….. … Smirnov, Alexey Kashevnik, and Igor Lashkov Improving Automatic Speech Recognition Containing Additive Noise Using Deep Denoising Autoencoders of LSTM …

Assisting discussion forum users using deep recurrent neural networks
JHP Suorra, O Mogren – Proceedings of the 1st Workshop on …, 2016 – aclweb.org
… Other approaches have been using con- volutional neural networks (Blunsom et al., 2014), and sequential denoising autoencoders (Hill et al., 2016). 58 Page 73. Dialog systems, also known as conversational agents, typically focus on learning to produce a well-formed …

Reading Comprehension using Entity-based Memory Network
X Wang, K Sudoh, M Nagata, T Shibata… – arXiv preprint arXiv …, 2016 – arxiv.org
… 1412.3555 (2014) 3. Dodge, J., Gane, A., Zhang, X., Bordes, A., Chopra, S., Miller, A., Szlam, A., Weston, J.: Evaluating prerequisite qualities for learning end-to-end dialog systems. … Li, J., Luong, MT, Jurafsky, D.: A hierarchical neural autoencoder for paragraphs and doc- uments …

Assisting Discussion Forum Users using Deep Recurrent Neural Networks
J Suorra Hagstedt P, O Mogren – Proceedings of the …, 2016 – publications.lib.chalmers.se
… Other approaches have been using con- volutional neural networks (Blunsom et al., 2014), and sequential denoising autoencoders (Hill et al., 2016). Page 7. Dialog systems, also known as conversational agents, typically focus on learning to produce a well-formed response …

A Sentence Interaction Network for Modeling Dependence between Sentences.
B Liu, M Huang, S Liu, X Zhu, X Zhu – ACL (1), 2016 – aclweb.org
… Socher et al. (2011) model the two sen- tences with Recursive Neural Networks (Unfold- ing Recursive Autoencoders), and then feed sim- ilarity scores between words and phrases (syntax tree nodes) to a CNN with dynamic pooling to cap- ture sentence interactions. Hu et al. …

Erica: The erato intelligent conversational android
DF Glas, T Minato, CT Ishi, T Kawahara… – Robot and Human …, 2016 – ieeexplore.ieee.org
… interactive capabilities. ACKNOWLEDGMENT We would like to thank Jani Even, Florent Ferreri, Koji Inoue, and Kurima Sakai for their contributions to ERICA’s control software, dialog system, and sensor network. REFERENCES [1 …

Ranking Responses Oriented to Conversational Relevance in Chat-bots.
B Wu, B Wang, H Xue – COLING, 2016 – aclweb.org
… 2015. A hierarchical neural autoencoder for paragraphs and documents. arXiv preprint arXiv:1506.01057. Ryan Lowe, Nissan Pow, Iulian Serban, and Joelle Pineau. 2015. The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems. …

Neural Networks for Natural Language Processing
L Mou – sei.pku.edu.cn
… [13] Socher R, et al. Semisupervised recursive autoencoders for predicting sentiment distributions. EMNLP, 2011 … Motivation: We don’t have the ground truth In a dialogue system, “The nature of of opendomain conversations shows that a variety of replies are plausible, but …

Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project
G Barzdins, S Renals, D Gosko – arXiv preprint arXiv:1604.01221, 2016 – arxiv.org
… of a single state-of-the-art sentence- level translational autoencoder requires days … Once produced within SUMMA project, these translational autoencoders with shared vectorspace will be a … of the neural networks, which is already applied in the neural dialogue systems such as …

Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks
J Kabbara, JCK Cheung – EMNLP 2016, 2016 – aclweb.org
… The model is a vari- ant of an autoencoder where the latent representa- tion has two separate components: one for style and one for content. … 2015. Seman- tically conditioned lstm-based natural language gener- ation for spoken dialogue systems. …

Learning interactive behavior for service robots the challenge of mixed-initiative interaction
P Liu, DF Glas, T Kanda, H Ishiguro – Proceedings of the Workshop on …, 2016 – irc.atr.jp
… were recognized in an imitative game using a hidden Markov model [8]. Data-driven dialogue systems have been … 5, we used autoencoders trained on a vectorization of the input text. … This vector was then input to a 4-layer autoencoder with 800 hidden units in each layer, then …

A Review on Deep Learning Algorithms for Speech and Facial Emotion Recognition
CP Latha, M Priya – APTIKOM Journal on Computer Science …, 2016 – jurnal.aptikom.or.id
… 2.4. Stacked Auto Encoders (SAE) The idea behind the auto encoder is based on the concept of a well-built representation of any model. An encoder is a mapping ?f that transforms an input vector iinto a hidden layer representation h …

Neural Discourse Modeling of Conversations
JM Pierre, M Butler, J Portnoff, L Aguilar – arXiv preprint arXiv:1607.04576, 2016 – arxiv.org
… [14] J. Li, MT Luong, and D. Jurafsky. A hierarchical neu- ral autoencoder for paragraphs and documents. … The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems. arXiv preprint arXiv:1506.08909, 2015. …

A Simple, Fast Diverse Decoding Algorithm for Neural Generation
J Li, W Monroe, D Jurafsky – arXiv preprint arXiv:1611.08562, 2016 – arxiv.org
Page 1. A Simple, Fast Diverse Decoding Algorithm for Neural Generation Jiwei Li, Will Monroe and Dan Jurafsky Computer Science Department, Stanford University, Stanford, CA, USA jiweil,wmonroe4,jurafsky@stanford.edu Abstract …

Compositional Sentence Representation from Character within Large Context Text
G Kim, H Lee, J Choi, S Lee – arXiv preprint arXiv:1605.00482, 2016 – arxiv.org
… The HCRN was tested on a spoken dialogue act classification task. The dialogue act (DA) is the communicative intention of a speaker for each sen- tence. Prediction of the DA can be further used as an input to modules in dialogue systems such as dialogue manager. …

Detecting paralinguistic events in audio stream using context in features and probabilistic decisions
R Gupta, K Audhkhasi, S Lee, S Narayanan – Computer Speech & …, 2016 – Elsevier
Non-verbal communication involves encoding, transmission and decoding of non-lexical cues and is realized using vocal (eg prosody) or visual (eg gaze, body.

Talking with ERICA, an autonomous android.
K Inoue, P Milhorat, D Lala, T Zhao, T Kawahara – SIGDIAL Conference, 2016 – aclweb.org
… In recent years, dialogue systems have been actively studied in the field of counsel- ing and diagnoses (DeVault et al., 2014). … To realize the dis- tant speech recognition, the enhanced speech is processed by a denoising auto encoder (DAE) to suppress reverberation …

Semantic language models with deep neural networks
AO Bayer, G Riccardi – Computer Speech & Language, 2016 – Elsevier
… Language modeling; Recurrent neural networks; Frame semantics; Semantic language models; Deep autoencoders. … This may lead to problems especially for spoken dialog systems, where one of the main goals of these systems is to extract user intentions and the meaning of …

Knowledge Enhanced Hybrid Neural Network for Text Matching
Y Wu, W Wu, Z Li, M Zhou – arXiv preprint arXiv:1611.04684, 2016 – arxiv.org
Page 1. Knowledge Enhanced Hybrid Neural Network for Text Matching Yu Wu†? , Wei Wu‡ , Zhoujun Li† , Ming Zhou‡ †State Key Lab of Software Development Environment, Beihang University, Beijing, China ‡ Microsoft …

An empirical investigation of word class-based features for natural language understanding
A Celikyilmaz, R Sarikaya, M Jeong… – IEEE/ACM Transactions …, 2016 – dl.acm.org
… The first set is internally collected multimedia data from live deployment scenarios of a spoken dialog system designed for entertainment search for Xbox One game console. … Generic search utterances are sent by the dialog system to the Bing search engine. …

Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves
F Tian, B Gao, D He, TY Liu – arXiv preprint arXiv:1604.02038, 2016 – arxiv.org
… 1We did not use any recently developed algorithms for infer- ence and learning under deep neural networks such as variational autoencoder [Kingma and Welling, 2013] because they are designed for continuous hidden states while our model includes discrete vari- ables. …

Recent Improvements on Error Detection for Automatic Speech Recognition.
Y Estève, S Ghannay, N Camelin – MMDA@ ECAI, 2016 – pdfs.semanticscholar.org
… One can also notice that the use of an auto encoder to combine word embeddings is really useful to capture com … of word and semantic features for theme identification in telephone conversations’, in 6th International Work- shop on Spoken Dialog Systems (IWSDS 2015), (2015). …

Cross-corpus speech emotion recognition based on transfer non-negative matrix factorization
P Song, W Zheng, S Ou, X Zhang, Y Jin, J Liu… – Speech …, 2016 – Elsevier
… hot research topic in speech signal processing field. With the development of computer technologies, the demands for emotion recognition in new spoken dialogue systems are very urgent. It has been proven very useful in many …

Neural Paraphrase Generation with Stacked Residual LSTM Networks
A Prakash, SA Hasan, K Lee, V Datla, A Qadir… – arXiv preprint arXiv …, 2016 – arxiv.org
… 2014) have been applied to various NLP tasks with promising results, for example, in the areas of machine translation (Cho et al., 2014; Bahdanau et al., 2015), speech recognition (Li and Wu, 2015), language modeling (Vinyals et al., 2015), and dialogue systems (Serban et al …

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
J Su, K Duh, X Carreras – Proceedings of the 2016 Conference on …, 2016 – aclweb.org
… Speech-based and Multimodal Approaches for Human versus Computer Addressee Detection Abstract: As dialog systems become ubiquitous, we must learn how to detect when a system is spoken to, and avoid mistaking human-human speech as computer-directed input. …

Group Sparse CNNs for Question Sentence Classification with Answer Sets
M Ma, L Huang, B Xiang, B Zhou – 2016 – openreview.net
… Pooling Feed into NN for classification Group Sparse Auto-Encoder Convolutional Layer W T z h … Alireza Makhzani and Brendan Frey. K-sparse autoencoders. In International Conference on Learning Repre- sentations. 2014. Andrew Ng. Sparse autoencoder. 2011. …

Determining speaker attributes from stress-affected speech in emergency situations with hybrid SVM-DNN architecture
J Ahmad, M Sajjad, S Rho, S Kwon, MY Lee… – Multimedia Tools and …, 2016 – Springer
… and their emotions more efficiently [4]. Detecting speaker gender from a brief utterance is a challenging task with rapidly growing applications in communication, human-computer inter- action (HCI), telephone speech forensic analysis, and natural language dialog systems. …

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
K Knight, A Nenkova, O Rambow – … of the 2016 Conference of the North …, 2016 – aclweb.org
… 110 xxi Page 22. Multi-domain Neural Network Language Generation for Spoken Dialogue Systems Tsung-Hsien Wen, Milica Gašic, Nikola Mrkšic, Lina M. Rojas-Barahona, Pei-Hao Su, David Vandyke and Steve Young . . . . . …

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
K Erk, NA Smith – Proceedings of the 54th Annual Meeting of the …, 2016 – aclanthology.info
Page 1. The 54th Annual Meeting of the Association for Computational Linguistics Proceedings of the Conference, Vol. 1 (Long Papers) August 7-12, 2016 Berlin, Germany Page 2. Platinum Sponsors Gold Sponsors Silver Sponsors ii Page 3. Bronze Sponsors …

PersoNER: Persian Named-Entity Recognition
H Poostchi, E Zare Borzeshi, M Abdous… – The 26th International …, 2016 – opus.lib.uts.edu.au
… Applications Tim Baldwin Maria Liakata Dialog Processing and Dialog Systems, Multimodal Interfaces Nina Dethlefs Simon Keizer Giuseppe Riccardi Speech Recognition, Text-To-Speech, Spoken Language Understanding Florian Metze Chung-Hsien Wu …

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Y Matsumoto, R Prasad – Proceedings of COLING 2016, the 26th …, 2016 – aclweb.org
… Applications Tim Baldwin Maria Liakata Dialog Processing and Dialog Systems, Multimodal Interfaces Nina Dethlefs Simon Keizer Giuseppe Riccardi Speech Recognition, Text-To-Speech, Spoken Language Understanding Florian Metze Chung-Hsien Wu …

Text analytics in industry: Challenges, desiderata and trends
A Ittoo, LM Nguyen, A van den Bosch – Computers in Industry, 2016 – Elsevier
The recent decades have witnessed an unprecedented expansion in the volume of unstructured data in digital textual formats. Companies are now starting to recogn.

A Corpus for Event Localization
C Ward – 2016 – bir.brandeis.edu
… 14 3.3 Label frequencies for full and function label sets . . . . . 15 4.1 TDFC Pool classifier architecture . . . . . 23 4.2 Autoencoder architecture . . . . . 24 4.3 Learning curve for different models . . . . . …

Emotion Modelling via Speech Content and Prosody: In Computer Games and Elsewhere
B Schuller – Emotion in Games, 2016 – Springer
… often in combination with ‘deep learning’ approaches [25, 57] based on (sparse) auto-encoders or similar. … As an example, in [11] a sparse autoencoder is trained in both – the source … Watanabe S, Tachioka Y, Schuller B (2014) Deep recurrent de-noising auto-encoder and blind …

A New Approach of Facial Expression Recognition for Ambient Assisted Living
Y Yaddaden, A Bouzouane, M Adda… – Proceedings of the 9th …, 2016 – dl.acm.org
… The first one uses the DBN (Deep Belief Net- work) in order to detect the different components of the face. The second one takes as input the different component and performs classification with SA (Stacked Autoencoder). The …

Transfer learning for cross-lingual sentiment classification with weakly shared deep neural networks
G Zhou, Z Zeng, JX Huang, T He – … of the 39th International ACM SIGIR …, 2016 – dl.acm.org
… Several auto-encoders can be used as building blocks to form a Stacked Auto-Encoders (SAEs) [4, 42]. Once an auto-encoder has been trained, one can stack another auto-encoder on top of it, by training a second one which sees the latent representation of the first one as …

Deep learning for sentiment analysis
LM Rojas?Barahona – Language and Linguistics Compass, 2016 – Wiley Online Library
… 4.2.1 Recursive autoencoders. The seminal work of Socher et al. (2011) introduced semi-supervised recursive autoencoders (RAE). … Instance of a recursive autoencoder applied to a binary tree. Taken from Socher et al. (2011). Each node of the tree is a vector of units. …

Recurrent neural network grammars
C Dyer, A Kuncoro, M Ballesteros, NA Smith – arXiv preprint arXiv …, 2016 – arxiv.org
Page 1. Recurrent Neural Network Grammars Chris Dyer? Adhiguna Kuncoro? Miguel Ballesteros?? Noah A. Smith? ?School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA ?NLP Group, Pompeu Fabra …

Emotion Recognition from Speech with Acoustic, Non-Linear and Wavelet-based Features Extracted in Different Acoustic Conditions
JC Vásquez Correa – 2016 – bibliotecadigital.udea.edu.co
… Page 20. 2 Introduction efforts are devoted to increasing accessibility and efficiency of spoken dialogue systems by integrating emotional and other paralinguistic cues [2]. There are a great deal of potential application that may use technologies related to …

STRESS RECOGNITION FROM SPEECH SIGNAL
M STAN?K – vutbr.cz
Page 1. VYSOKÉ U?ENÍ TECHNICKÉ V BRN? BRNO UNIVERSITY OF TECHNOLOGY FAKULTA ELEKTROTECHNIKY A KOMUNIKA?NÍCH TECHNOLOGIÍ ÚSTAV RADIOELEKTRONIKY FACULTY OF ELECTRICAL ENGINEERING …

Context-aware Natural Language Generation with Recurrent Neural Networks
J Tang, Y Yang, S Carton, M Zhang, Q Mei – arXiv preprint arXiv …, 2016 – arxiv.org
… (Bowman et al. 2015) investigated generat- ing sentences from continuous semantic spaces with a vari- ational auto-encoder, in which RNN is used for both the en- coder and the encoder. … Stochastic lan- guage generation for spoken dialogue systems. …

Designing Regularizers and Architectures for Recurrent Neural Networks
D Krueger – 2016 – papyrus.bib.umontreal.ca
… 57 6.1.1 Gated autoencoders . . . . . … 60 Page 9. LIST OF ABBREVIATIONS AE Autoencoder AGI Artificial General Intelligence AI Artificial Intelligence ANN Artificial Neural Network BLEU Bilingual Evaluation Understudy BN Batch Normalization …

Deep learning in the automotive industry: Applications and tools
A Luckow, M Cook, N Ashcraft, E Weill… – Big Data (Big Data) …, 2016 – ieeexplore.ieee.org
… Voice dialog systems will become more natural and interactive with deep learning allowing a hands-free interaction with the vehicle … advances have been made in automatically learning features (also referred to as representation learning), through auto-encoders, sparse coders …

Machine Learning: The New AI
E Alpaydin – 2016 – books.google.com
Page 1. MACHINE LEARNING ETHEM ALPAYDIN O 1 000 1 0 1 0 1 1 1 0 1 000 1 1 0 1 000 O 1 1 00 1 0 1 0 1 1 0 1 1 0 1 00 1 00000 O 1 00000 1 0 1 1 0 1 1 000 1 1 1 0000 O 1 1 0000 1 0 1 1 1 1 00 1 0 1 1 00 1 00 O 1 1 0 …

1st International Workshop on Multimodal Media Data Analytics (MMDA 2016)
S Vrochidis, M Melero, L Wanner, J Grivolla, Y Estève… – ecai2016.org
Page 1. ECAI 2016, MMDA 2016 workshop, August 2016 1st International Workshop on Multimodal Media Data Analytics (MMDA 2016) The rapid advancements of digital technologies, as well as the penetration of internet and …

Analysis and modeling for robust whispered speech recognition
S Ghaffarzadegan – 2016 – search.proquest.com
… The second strategy generates pseudo-whisper samples by means of denoising autoencoders (DAE). … 68CHAPTER 8 DENOISING AUTOENCODER COMPENSATION METHOD . . . 698.1 Denoising Autoencoder . . . . . …

From predictive to interactive multimodal language learning
A Lazaridou – 2016 – eprints-phd.biblio.unitn.it
… by [90], who use more advanced visual representations relying on images annotated with high-level “visual attributes”, and a multimodal fusion strategy based on stacked autoencoders. [49] adopt instead a simple concatenation strategy, but obtain empir- …

Large-scale affective computing for visual multimedia
B Jou – 2016 – search.proquest.com
Large-scale affective computing for visual multimedia. Abstract. In recent years, Affective Computing has arisen as a prolific interdisciplinary field for engineering systems that integrate human affections. While human-computer …

Discriminative Acoustic Features for Deployable Speech Recognition
A Faria – 2016 – eecs.berkeley.edu
… the HMM’s topology. One of the most interesting recent advances in discriminative acoustic feature extraction using deep neural networks has been the development of auto-encoder bottleneck features [23]. This was inspired …