Idiap Publications - Public RSS - Aigaion 2.0 Idiap Publications - Public RSS - Aigaion 2.0 http://publications.idiap.ch/index.php Aigaion.nl An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation Tong, Sibo, Garner, Philip N. and Bourlard, Hervé: "An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation" http://publications.idiap.ch/index.php/publications/show/3634 Characterisation of voice quality of Parkinson's disease using differential phonological posterior features Cernak, Milos, Orozco-Arroyave, Juan Rafael, Rudzicz, Frank, Christensen, Heidi, Vasquez-Correa, Juan Camilo and Nöth, Elmar: "Characterisation of voice quality of Parkinson's disease using differential phonological posterior features" http://publications.idiap.ch/index.php/publications/show/3633 MAAYA: Multimedia Methods to Support Maya Epigraphic Analysis Gatica-Perez, Daniel, Can, Gulcan, Hu, Rui, Marchand-Maillet, Stephane, Odobez, Jean-Marc, Pallan Gayol, Carlos and Roman-Rangel, Edgar: "MAAYA: Multimedia Methods to Support Maya Epigraphic Analysis" http://publications.idiap.ch/index.php/publications/show/3629 Towards large scale multimedia indexing: A case study on person discovery in broadcast news Le, Nam and Odobez, Jean-Marc: "Towards large scale multimedia indexing: A case study on person discovery in broadcast news" http://publications.idiap.ch/index.php/publications/show/3626 Shape Representations for Maya Codical Glyphs: Knowledge-driven or Deep? Can, Gulcan, Odobez, Jean-Marc and Gatica-Perez, Daniel: "Shape Representations for Maya Codical Glyphs: Knowledge-driven or Deep?" http://publications.idiap.ch/index.php/publications/show/3624 Bob Speaks Kaldi Cernak, Milos, Komaty, Alain, Mohammadi, Amir, Anjos, André and Marcel, Sébastien: "Bob Speaks Kaldi" http://publications.idiap.ch/index.php/publications/show/3623 Characterisation of voice quality of Parkinson's disease using differential phonological posterior features Cernak, Milos, Orozco-Arroyave, Juan Rafael, Rudzicz, Frank, Christensen, Heidi, Vasquez-Correa, Juan Camilo and Nöth, Elmar: "Characterisation of voice quality of Parkinson's disease using differential phonological posterior features" http://publications.idiap.ch/index.php/publications/show/3620 An Approach for Imitation Learning on Riemannian Manifolds Zeestraten, M., Havoutis, I., Silverio, J., Calinon, S. and Caldwell, D. G.: "An Approach for Imitation Learning on Riemannian Manifolds" http://publications.idiap.ch/index.php/publications/show/3619 Learning adaptive dressing assistance from human demonstration Pignat, E. and Calinon, S.: "Learning adaptive dressing assistance from human demonstration" http://publications.idiap.ch/index.php/publications/show/3618 Insiders and Outsiders: Comparing Urban Impressions between Population Groups Santani, Darshan, Ruiz-Correa, Salvador and Gatica-Perez, Daniel: "Insiders and Outsiders: Comparing Urban Impressions between Population Groups" http://publications.idiap.ch/index.php/publications/show/3617 Subspace Regularized Dynamic Time Warping for Spoken Query Detection Ram, Dhananjay, Asaei, Afsaneh and Bourlard, Hervé: "Subspace Regularized Dynamic Time Warping for Spoken Query Detection" http://publications.idiap.ch/index.php/publications/show/3616 Sparse Pronunciation Codes for Perceptual Phonetic Information Assessment Asaei, Afsaneh, Cernak, Milos, Bourlard, Hervé and Ram, Dhananjay: "Sparse Pronunciation Codes for Perceptual Phonetic Information Assessment" http://publications.idiap.ch/index.php/publications/show/3612 2D Face Recognition: An Experimental and Reproducible Research Survey Günther, Manuel, El Shafey, Laurent and Marcel, Sébastien: "2D Face Recognition: An Experimental and Reproducible Research Survey" http://publications.idiap.ch/index.php/publications/show/3608 Topic and Sentiment in Phrase-Based Statistical Machine Translation Habibi, Maryam, Pappas, Nikolaos and Popescu-Belis, Andrei: "Topic and Sentiment in Phrase-Based Statistical Machine Translation" http://publications.idiap.ch/index.php/publications/show/3603 Analyzing and Visualizing Ancient Maya Hieroglyphics Using Shape: from Computer Vision to Digital Humanities Hu, Rui, Pallan Gayol, Carlos, Odobez, Jean-Marc and Gatica-Perez, Daniel: "Analyzing and Visualizing Ancient Maya Hieroglyphics Using Shape: from Computer Vision to Digital Humanities" http://publications.idiap.ch/index.php/publications/show/3601 Robust and Accurate 3D Head Pose Estimation through 3DMM and Online Head Model Reconstruction Yu, Yu, Funes Mora, Kenneth Alberto and Odobez, Jean-Marc: "Robust and Accurate 3D Head Pose Estimation through 3DMM and Online Head Model Reconstruction" http://publications.idiap.ch/index.php/publications/show/3597 Robust and Accurate 3D Head Pose Estimation through 3DMM and Online Head Model Reconstruction Yu, Yu, Funes Mora, Kenneth Alberto and Odobez, Jean-Marc: "Robust and Accurate 3D Head Pose Estimation through 3DMM and Online Head Model Reconstruction" http://publications.idiap.ch/index.php/publications/show/3596 A Posterior-Based Multi-Stream Formulation for G2P Conversion Razavi, Marzieh and Magimai.-Doss, Mathew: "A Posterior-Based Multi-Stream Formulation for G2P Conversion" http://publications.idiap.ch/index.php/publications/show/3595 Object Detection with Active Sample Harvesting Canévet, Olivier: "Object Detection with Active Sample Harvesting" http://publications.idiap.ch/index.php/publications/show/3594 Large-Scale Image Segmentation with Convolutional Networks Pinheiro, Pedro H. O.: "Large-Scale Image Segmentation with Convolutional Networks" http://publications.idiap.ch/index.php/publications/show/3592 Using Coreference Links to Improve Spanish-to-English Machine Translation Miculicich Werlen, Lesly and Popescu-Belis, Andrei: "Using Coreference Links to Improve Spanish-to-English Machine Translation" http://publications.idiap.ch/index.php/publications/show/3591 Using Coreference Links to Improve Spanish-to-English Machine Translation Miculicich Werlen, Lesly and Popescu-Belis, Andrei: "Using Coreference Links to Improve Spanish-to-English Machine Translation" http://publications.idiap.ch/index.php/publications/show/3590 Machine translation of Spanish personal and possessive pronouns using anaphora probabilities Luong, Ngoc-Quang and Popescu-Belis, Andrei: "Machine translation of Spanish personal and possessive pronouns using anaphora probabilities" http://publications.idiap.ch/index.php/publications/show/3589 Machine translation of Spanish personal and possessive pronouns using anaphora probabilities Luong, Ngoc-Quang and Popescu-Belis, Andrei: "Machine translation of Spanish personal and possessive pronouns using anaphora probabilities" http://publications.idiap.ch/index.php/publications/show/3588 Explicit Document Modeling through Weighted Multiple-Instance Learning Pappas, Nikolaos and Popescu-Belis, Andrei: "Explicit Document Modeling through Weighted Multiple-Instance Learning" http://publications.idiap.ch/index.php/publications/show/3585 Multilingual Visual Sentiment Concept Clustering and Analysis Pappas, Nikolaos, Redi, Miriam, Topkara, Mercan, Liu, Hongyi, Jou, Brendan, Chen, Tao and Chang, Shih-Fu: "Multilingual Visual Sentiment Concept Clustering and Analysis" http://publications.idiap.ch/index.php/publications/show/3584 Real-time Multiple Head Tracking Using Texture and Colour Cues Khalidov, Vasil and Odobez, Jean-Marc: "Real-time Multiple Head Tracking Using Texture and Colour Cues" http://publications.idiap.ch/index.php/publications/show/3582 Intonation Modelling for Speech Synthesis and Emphasis Preservation Honnet, Pierre-Edouard: "Intonation Modelling for Speech Synthesis and Emphasis Preservation" http://publications.idiap.ch/index.php/publications/show/3581 The SIWIS French Speech Synthesis Database – Design and recording of a high quality French database for speech synthesis Honnet, Pierre-Edouard, Lazaridis, Alexandros, Garner, Philip N. and Yamagishi, Junichi: "The SIWIS French Speech Synthesis Database – Design and recording of a high quality French database for speech synthesis" http://publications.idiap.ch/index.php/publications/show/3580 On the Impact of Non-modal Phonation On Phonological Features Cernak, Milos, Nöth, Elmar, Rudzicz, Frank, Christensen, Heidi, Orozco-Arroyave, Juan Rafael, Arora, Raman, Bocklet, Tobias, Chinaei, Hamidreza, Hannink, Julius, Nidadavolu, Phani Sankar, Vasquez, Juan Camilo, Yancheva, Maria, Vann, Alyssa and Vogler, Nikolai: "On the Impact of Non-modal Phonation On Phonological Features" http://publications.idiap.ch/index.php/publications/show/3578 Multi-view Representation Learning Via GCCA for Multimodal Analysis of Parkinson's Disease Vasquez-Correa, Juan Camilo, Orozco-Arroyave, Juan Rafael, Arora, Raman, Nöth, Elmar, Dehak, Najim, Christensen, Heidi, Rudzicz, Frank, Bocklet, Tobias, Cernak, Milos, Chinaei, Hamidreza, Hannink, Julius, Nidadavolu, Phani Sankar, Yancheva, Maria, Vann, Alyssa and Vogler, Nikolai: "Multi-view Representation Learning Via GCCA for Multimodal Analysis of Parkinson's Disease" http://publications.idiap.ch/index.php/publications/show/3577 Towards Weakly Supervised Acoustic Subword Unit Discovery and Lexicon Development Using Hidden Markov Models Razavi, Marzieh, Rasipuram, Ramya and Magimai.-Doss, Mathew: "Towards Weakly Supervised Acoustic Subword Unit Discovery and Lexicon Development Using Hidden Markov Models" http://publications.idiap.ch/index.php/publications/show/3575 A MultiPath Network for Object Detection Zagoruyko, Sergey, Lerer, Adam, Lin, Tsung-Yi, Pinheiro, Pedro H. O., Gross, Sam, Chintala, Soumith and Dollar, Piotr: "A MultiPath Network for Object Detection" http://publications.idiap.ch/index.php/publications/show/3573 Learning to Refine Object Segments Pinheiro, Pedro H. O., Lin, Tsung-Yi, Collobert, Ronan and Dollar, Piotr: "Learning to Refine Object Segments" http://publications.idiap.ch/index.php/publications/show/3572 Unsupervised Interpretable Pattern Discovery in Time Series Using Autoencoders Bascol, Kevin, Emonet, Remi, Fromont, Elisa and Odobez, Jean-Marc: "Unsupervised Interpretable Pattern Discovery in Time Series Using Autoencoders" http://publications.idiap.ch/index.php/publications/show/3571 CRF-Based Context Modeling for Person Identification in Broadcast Videos Gay, Paul, Meignier, Sylvain, Deleglise, Paul and Odobez, Jean-Marc: "CRF-Based Context Modeling for Person Identification in Broadcast Videos" http://publications.idiap.ch/index.php/publications/show/3570 Consistent Translation of Repeated Nouns using Syntactic and Semantic Cues Pu, Xiao, Mascarell, Laura and Popescu-Belis, Andrei: "Consistent Translation of Repeated Nouns using Syntactic and Semantic Cues" http://publications.idiap.ch/index.php/publications/show/3567 Consistent Translation of Repeated Nouns using Syntactic and Semantic Cues Pu, Xiao, Mascarell, Laura and Popescu-Belis, Andrei: "Consistent Translation of Repeated Nouns using Syntactic and Semantic Cues" http://publications.idiap.ch/index.php/publications/show/3566 Manual and automatic labeling of discourse connectives for machine translation (Keynote paper) Popescu-Belis, Andrei: "Manual and automatic labeling of discourse connectives for machine translation (Keynote paper)" http://publications.idiap.ch/index.php/publications/show/3565 Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction Guillou, Liane, Hardmeier, Christian, Nakov, Preslav, Stymne, Sara, Tiedemann, Jorg, Versley, Yannick, Cettolo, Mauro, Webber, Bonnie and Popescu-Belis, Andrei: "Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction" http://publications.idiap.ch/index.php/publications/show/3564 Comparing Two Strategies for Query Expansion in a News Monitoring System Mahdabi, Parvaz and Popescu-Belis, Andrei: "Comparing Two Strategies for Query Expansion in a News Monitoring System" http://publications.idiap.ch/index.php/publications/show/3563 Towards building an attentive artificial listener: on the perception of attentiveness in audio-visual feedback tokens Oertel, Catharine, Lopes, José David, Yu, Yu, Funes Mora, Kenneth Alberto, Gustafson, Joakim, Black, Alan and Odobez, Jean-Marc: "Towards building an attentive artificial listener: on the perception of attentiveness in audio-visual feedback tokens" http://publications.idiap.ch/index.php/publications/show/3560 EXPLOITING SEQUENCE INFORMATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION Dey, Subhadeep, Motlicek, Petr, Madikeri, Srikanth and Ferras, Marc: "EXPLOITING SEQUENCE INFORMATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION" http://publications.idiap.ch/index.php/publications/show/3559 EXPLOITING SEQUENCE INFORMATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION Dey, Subhadeep, Motlicek, Petr, Madikeri, Srikanth and Ferras, Marc: "EXPLOITING SEQUENCE INFORMATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION" http://publications.idiap.ch/index.php/publications/show/3556 Speaker Diarization and Linking of Meeting Data Ferras, Marc, Madikeri, Srikanth and Bourlard, Hervé: "Speaker Diarization and Linking of Meeting Data" http://publications.idiap.ch/index.php/publications/show/3552 INTRA-CLASS COVARIANCE ADAPTATION IN PLDA BACK-ENDS FOR SPEAKER VERIFICATION Madikeri, Srikanth, Ferras, Marc, Motlicek, Petr and Dey, Subhadeep: "INTRA-CLASS COVARIANCE ADAPTATION IN PLDA BACK-ENDS FOR SPEAKER VERIFICATION" http://publications.idiap.ch/index.php/publications/show/3549 Two-Pass IB based Speaker Diarization System using Meeting-Specific ANN based Features Dawalatabad, Nauman, Madikeri, Srikanth, Sekhar, C Chandra and Murthy, Hema A: "Two-Pass IB based Speaker Diarization System using Meeting-Specific ANN based Features" http://publications.idiap.ch/index.php/publications/show/3547 Computational Analysis of Urban Places Using Mobile Crowdsensing Santani, Darshan: "Computational Analysis of Urban Places Using Mobile Crowdsensing" http://publications.idiap.ch/index.php/publications/show/3543 Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models Dighe, Pranay, Asaei, Afsaneh and Bourlard, Hervé: "Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models" http://publications.idiap.ch/index.php/publications/show/3542 Long Term Spectral Statistics for Voice Presentation Attack Detection Muckenhirn, Hannah, Korshunov, Pavel, Magimai.-Doss, Mathew and Marcel, Sébastien: "Long Term Spectral Statistics for Voice Presentation Attack Detection" http://publications.idiap.ch/index.php/publications/show/3541