@article{J.2021,
title = {Facial emotions are accurately encoded in the brains of those with autism: A deep learning approach},
author = {Torres M. J., Clarkson T., Hauschild K., Luhmann C. C., Lerner D. M. and Riccardi G.},
url = {https://www.sciencedirect.com/science/article/abs/pii/S2451902221001075?via%3Dihub},
year = {2021},
date = {2021-04-16},
journal = {Biological Psychiatry: Cognitive Neuroscience and Neuroimaging},
keywords = {Affective Computing, Autism, Machine Learning, Signal Annotation and Interpretation}
}

@article{A.2018b,
title = {Depression Severity Estimation from Multiple Modalities},
author = {Stepanov E. A., Lathuilierev S., Chowdhury S. A., Ghosh A., Vieriu R.D., Sebe N. and Riccardi G.},
editor = {IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom), Ostrava},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2019/11/HealthCom18-Depression.pdf},
year = {2018},
date = {2018-01-01},
note = {EXCELLENT Paper AWARD},
keywords = {Health Analytics, Machine Learning}
}

@article{F.2015,
title = {In the mood for Sharing Contents: Emotions, personality and interaction styles in the diffusion of news},
author = {Celli F., Ghosh A., Alam F. and Riccardi G.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2015/11/IPM15-MoodSharing.pdf},
year = {2015},
date = {2015-11-01},
journal = {Information Processing and Management, Nov 2015},
abstract = {In this paper, we analyze the influence of Twitter users in sharing news articles that may affect the readers’ mood. We collected data of more than 2000 Twitter users who shared news articles from Corriere.it, a daily newspaper that provides mood metadata annotated by readers on a voluntary basis. We automatically annotated personality types and communication styles of Twitter users and analyzed the correlations between personality, communication style, Twitter metadata (such as followig and folllowers) and the type of mood associated to the articles they shared. We also run a feature selection task, to find the best predictors of positive and negative mood sharing, and a classification task. We automatically predicted positive and negative mood sharers with 61.7% F1-measure.},
keywords = {Machine Learning, Natural Language Processing, Signal Annotation and Interpretation}
}

@article{M2015,
title = {Predicting Students’ Final Exam Scores from their Course Activities},
author = {Mogessie M, Riccardi G. and Ronchetti M.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2015/11/FIE15-PredictingStudentsScores.pdf},
year = {2015},
date = {2015-10-21},
journal = {Proc. IEEE Frontiers in Education, El Paso ( USA), 2015.},
abstract = {A common approach to the problem of predicting students’ exam scores has been to base this prediction on the previous educational history of students. In this paper, we present a model that bases this prediction on students’ performance on several tasks assigned throughout the duration
of the course. In order to build our prediction model, we use data from a semi-automated peer-assessment system implemented in two undergraduate-level computer science courses, where students ask questions about topics discussed in class, answer questions from their peers, and rate answers provided by their peers. We then construct features that are used to build several multiple linear regression models. We use the Root Mean Squared Error (RMSE) of the prediction models to evaluate their performance. Our final model, which has recorded an RMSE of 2.9326 for one course and 3.4383 for another on predicting grades on a scale of 18 to 30, is built using 14 features that capture various activities of students. Our work has possible implications in the MOOC arena and in similar online course administration systems.},
keywords = {Education Analytics, Machine Learning}
}

@article{A.2015,
title = {Open Challenges in Modelling, Analysis and Synthesis of Human Behaviour in Human–Human and Human–Machine Interactions},
author = {Vinciarelli A., Esposito A., Andre’ E., Bonin F., Chetouani M., Cohn F. J., Cristani M., Fuhrmann F., Gilmartin E., Hammal Z., Heylen D., Kaiser R., Koutsombogera M., Potamianos A., Renals S., Riccardi G., Salah A. G.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2015/11/CogniComp15-ChallengesHHHM-Review.pdf},
year = {2015},
date = {2015-04-01},
journal = {Cognitive Computation, pp. 1-17, April 2015},
abstract = {Modelling, analysis and synthesis of behaviour are the subject of major efforts in computing science,
especially when it comes to technologies that make sense of human–human and human–machine interactions. This article outlines some of the most important issues that still need to be addressed to ensure substantial progress in the field, namely (1) development and adoption of virtuous data collection and sharing practices, (2) shift in the focus of interest from individuals to dyads and groups, (3) endowment of artificial agents with internal representations of users and context, (4) modelling of cognitive and semantic processes underlying social behaviour and (5) identification of application domains and strategies for moving from laboratory to the real-world products.},
keywords = {Conversational and Interactive Systems , Machine Learning, Speech Processing}
}

@article{R.2008,
title = {Spoken Language Understanding},
author = {De Mori R., Bechet F., Hakkani-Tur D., McTear M., Riccardi G. and Tur G.},
year = {2008},
date = {2008-01-01},
journal = {IEEE Signal Processing Magazine vol. 25, pp.50-58 ,2008},
keywords = {Machine Learning, Natural Language Processing, Speech Processing}
}

@article{G.2006,
title = {Spoken Dialog Systems: From Theory to Technology},
author = {Riccardi G. and Baggia P.},
year = {2006},
date = {2006-01-01},
journal = {Edizione della Normale di Pisa, 2006},
keywords = {Conversational and Interactive Systems , Machine Learning, Speech Processing}
}

@article{D.2006,
title = {An Active Approach to spoken Language Processing},
author = {Hakkani-Tur D., Riccardi G. and Tur G.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/acm-tslp-06.pdf},
year = {2006},
date = {2006-01-01},
journal = {ACM Transactions on Speech and Language Processing, Vol. 3, No. 3, pp 1-31, 2006},
abstract = {State of the art data-driven speech and language processing systems require a large amount of human intervention ranging from data annotation to system prototyping. In the traditional supervised passive approach, the system is trained on a given number of annotated data samples and evaluated using a separate test set. Then more data is collected arbitrarily, annotated, and the whole cycle is repeated. In this article, we propose the active approach where the system itself selects its own training data, evaluates itself and re-trains when necessary. We first employ active learning which aims to automatically select the examples that are likely to be the most informative for a given task. We use active learning for both selecting the examples to label and the examples to re-label in order to correct labeling errors. Furthermore, the system automatically evaluates itself using active evaluation to keep track of the unexpected events and decides on-demand to label more examples. The active approach enables dynamic adaptation of spoken language processing systems to unseen or unexpected events for nonstationary input while reducing the manual annotation effort significantly. We have evaluated the active approach with the AT&T spoken dialog system used for customer care applications. In this article, we present our results for both automatic speech recognition and spoken language understanding. Categories and Subject Descriptors: I.2.7 [Artificial Intelligence]: Natural Language Processing—Speech recognition and synthesis; I.5.1 [Pattern Recognition]: Models—Statistical General Terms: Algorithms, Languages, Performance Additional Key Words and Phrases: Passive learning, active learning, adaptive learning, unsupervised learning, active evaluation, spoken language understanding, automatic speech recognition, spoken dialog systems, speech and language processing},
keywords = {Machine Learning, Natural Language Processing, Speech Processing}
}

@article{N.2006,
title = {The AT&T Spoken Language Understanding System},
author = {Gupta N., Tur G., Hakkani-Tur D., Bangalore S., Riccardi G. and Rahim M.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/IEEE-SAP-2005-SLU.pdf},
year = {2006},
date = {2006-01-01},
journal = {IEEE Trans. on Audio, Speech and Language Processing, volume 14, Issue 1, pp. 213-22, 2006},
abstract = {Spoken language understanding (SLU) aims at extracting meaning from natural language speech. Over the past decade, a variety of practical goal-oriented spoken dialog systems have been built for limited domains. SLU in these systems ranges from understanding predetermined phrases through fixed grammars, extracting some predefined named entities, extracting users’ intents for call classification, to combinations of users’ intents and named entities. In this paper, we present the SLU system of VoiceTone ® (a service provided by AT&T where AT&T develops, deploys and hosts spoken dialog applications for enterprise customers). The SLU system includes extracting both intents and the named entities from the users’ utterances. For intent determination, we use statistical classifiers trained from labeled data, and for named entity extraction we use rule-based fixed grammars. The focus of our work is to exploit data and to use machine learning techniques to create scalable SLU systems which can be quickly deployed for new domains with minimal human intervention. These objectives are achieved by 1) using the predicate-argument representation of semantic content of an utterance; 2) extending statistical classifiers to seamlessly integrate hand crafted classification rules with the rules learned from data; and 3) developing an active learning framework to minimize the human labeling effort for quickly building the classifier models and adapting them to changes. We present an evaluation of this system using two deployed applications of VoiceTone},
keywords = {Machine Learning, Natural Language Processing, Speech Processing}
}

@article{Riccardi2005b,
title = {Active Learning: Theory and Applications to Automatic Speech Recognition},
author = {Riccardi G. and Hakkani-Tur D.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/ieee-al-05.pdf},
year = {2005},
date = {2005-01-01},
journal = {IEEE Trans. on Speech and Audio, vol. 13, n.4 , pp. 504-511, 2005},
abstract = {We are interested in the problem of adaptive learning in the context of automatic speech recognition (ASR). In this paper, we propose an active learning algorithm for ASR. Automatic speech recognition systems are trained using human supervision to provide transcriptions of speech utterances. The goal of Active Learning is to minimize the human supervision for training acoustic and language models and to maximize the performance given the transcribed and untranscribed data. Active learning aims at reducing the number of training examples to be labeled by automatically processing the unlabeled examples, and then selecting the most informative ones with respect to a given cost function for a human to label. In this paper we describe how to estimate the confidence score for each utterance through an on-line algorithm using the lattice output of a speech recognizer. The utterance scores are filtered through the informativeness function and an optimal subset of training samples is selected. The active learning algorithm has been applied to both batch and on-line learning scheme and we have experimented with different selective sampling algorithms. Our experiments show that by using active learning the amount of labeled data needed for a given word accuracy can be reduced by more than 60% with respect to random sampling.},
keywords = {Machine Learning}
}

@article{A.2005,
title = {Adaptive Categorical Understanding for Spoken Dialogue Systems'},
author = {Potamianos A., Narayanan S. and Riccardi G.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/ieee_adapt-categ-05.pdf},
year = {2005},
date = {2005-01-01},
journal = {Potamianos A., Narayanan S and Riccardi, G.},
abstract = {IEEE Trans. on Speech and Audio, vol. 13, n.3 , pp. 321-329, 2005},
keywords = {Conversational and Interactive Systems , Machine Learning, Speech Processing}
}

@article{M.2001,
title = {Robust Numeric Recognition in Spoken Language Dialogue},
author = {Rahim M., Riccardi G., Saul L., Wright J., Buntschuh B. and Gorin A. L.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/numericlang-speechcomm-2001.pdf},
year = {2001},
date = {2001-11-01},
journal = {Speech Communication, 34, pp. 195-212, 2001},
abstract = {This paper addresses the problem of automatic numeric recognition and understanding in spoken language dialogue. We show that accurate numeric understanding in ̄uent unconstrained speech demands maintaining robustness at several di€erent levels of system design, including acoustic, language, understanding and dialogue. We describe a robust system for numeric recognition and present algorithms for feature extraction, acoustic and language modeling, discriminative training, utterance veri®cation and numeric understanding and validation. Experimental results from a ®eld-trial of a spoken dialogue system are presented that include customers\' responses to credit card and telephone number requests. Ó 2001 Elsevier Science B.V. All rights reserved.},
keywords = {Machine Learning, Signal Annotation and Interpretation, Speech Processing}
}

@article{C.2001,
title = {Integration of Utterance Verification with Statistical Language Modeling and Spoken Language Understanding},
author = {Rose R. C., Yao H., Riccardi G. and Wright J. H.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/uv-speechcomm-2001.pdf},
year = {2001},
date = {2001-01-01},
journal = {Speech Communication, 34, pp. 321-331, 2001},
abstract = {Methods for utterance veri®cation (UV) and their integration into statistical language modeling and understanding formalisms for a large vocabulary spoken understanding system are presented. The paper consists of three parts. First, a set of acoustic likelihood ratio (LR) based UV techniques are described and applied to the problem of rejecting portions of a hypothesized word string that may have been incorrectly decoded by a large vocabulary continuous speech recognizer. Second, a procedure for integrating the acoustic level con®dence measures with the statistical language model is described. Finally, the e€ect of integrating acoustic level con®dence into the spoken language understanding unit (SLU) in a call-type classi®cation task is discussed. These techniques were evaluated on utterances collected from a highly unconstrained call routing task performed over the telephone network. They have been evaluated in terms of their ability to classify utterances into a set of 15 call-types that are accepted by the application. Ó 2001 Elsevier Science B.V. All rights reserved.},
keywords = {Machine Learning, Signal Annotation and Interpretation, Speech Processing}
}

@article{Bocchieri1995,
title = {Understanding spontaneous speech},
author = {Bocchieri E., Levin E., Pieraccini R. and Riccardi G.},
year = {1995},
date = {1995-01-01},
journal = {J. of the Italian Assoc. of Artificial Intelligence, Sept. 1995},
keywords = {Machine Learning, Signal Annotation and Interpretation, Speech Processing}
}