Multimodal Analyses enabling Artificial Agents in Human-Machine Interaction

This book constitutes the thoroughly refereed post-workshop proceedings of the Second Workshop on Multimodal Analyses Enabling Artificial Agents in Human Interaction, MA3HMI 2014, held in Conjunction with INTERSPEECH 2014, in Singapore, Singapore, on September 14th, 2014.The 9 revised papers presented together with a keynote talk were carefully reviewed and selected from numerous submissions. They are organized in two sections: human-machine interaction and dialogs and speech recognition.

Includes supplementary material: sn.pub/extras

Annotating the TCD D-ANS Corpus - A Multimodal Multimedia Monolingual Biometric Corpus of Spoken Social Interaction.- Steps Towards More Natural Human-Machine Interaction via Audio-Visual Word Prominence Detection.- Improving Robustness Against Environmental Sounds for Directing Attention of Social Robots.- On Annotation and Evaluation of Multi-modal Corpora in Affective Human-Computer Interaction.- Modelling User Experience in Human-Robot Interactions.- Disposition Recognition from Spontaneous Speech Towards a Combination with Co-speech Gestures.- ASR Independent Hybrid Recurrent Neural Network Based Error Correction for Dialog System Applications.- Acquisition and Use of Long-Term Memory for Personalized Dialog Systems.- An Automatic Shout Detection System Using Speech Production Features.- Collecting Data for Automatic Speech Recognition Systems in Dialectal Arabic Using Games with a Purpose.- A Multimodal Multimedia Monolingual Biometric Corpus of Spoken Social Interaction.- Steps Towards More Natural Human-Machine Interaction via Audio-Visual Word Prominence Detection.- Improving Robustness Against Environmental Sounds for Directing Attention of Social Robots.- On Annotation and Evaluation of Multi-modal Corpora in Affective Human-Computer Interaction.- Modelling User Experience in Human-Robot Interactions.-Disposition Recognition from Spontaneous Speech Towards a Combination with Co-speech Gestures.- ASR Independent Hybrid Recurrent Neural Network Based Error Correction for Dialog System Applications.- Acquisition and Use of Long-Term Memory for Personalized Dialog Systems.- An Automatic Shout Detection System Using Speech Production Features.- Collecting Data for Automatic Speech Recognition Systems in Dialectal Arabic Using Games with a Purpose.