@article{M.2021,
title = {A Participatory Design of Conversational Artificial Intelligence Agents for Mental Healthcare},
author = {Danieli M., Ciulli T, Mousavi M. and Riccardi G.},
url = {https://formative.jmir.org/2021/12/e30053},
year = {2021},
date = {2021-04-29},
journal = {Journal of Medical Internet Research (JMIR) Formative Research Journal},
volume = {5},
number = {12},
keywords = {Conversational and Interactive Systems , Signal Annotation and Interpretation}
}

@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{F.2018,
title = {Annotating and Modeling Empathy in Spoken Conversations},
author = {Alam F., Danieli M. and Riccardi G.},
url = {https://www.sciencedirect.com/science/article/pii/S088523081730133X},
year = {2018},
date = {2018-07-01},
journal = {Computer Speech and Language},
volume = {50},
pages = {40-61},
keywords = {Affective Computing, Discourse, Signal Annotation and Interpretation}
}

@article{E.2017,
title = {Cross-Language Transfer of Semantic Annotation via Targeted Crowdsourcing: Task Design and Evaluation},
author = {Stepanov A. E., Chowdhury A. S., Bayer A. O., Ghosh A., Klasinas I., Calvo M., Sanchis E. and Riccardi G.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2017/10/10.1007s10579-017-9396-5.pdf},
year = {2017},
date = {2017-01-01},
journal = {Language Resources and Evaluation, https://doi.org/10.1007/s10579-017-9396-5 , Springer, 2017},
abstract = {Modern data-driven spoken language systems (SLS) require manual semantic annotation for training spoken language understanding parsers. Multilingual porting of SLS demands significant manual effort and language resources, as this manual annotation has to be replicated. Crowdsourcing is an accessible and cost-effective alternative to traditional methods of collecting and annotating data. The application of crowdsourcing to simple tasks has been well investigated. However, complex tasks, like cross-language semantic annotation transfer, may generate low judgment agreement and/or poor performance. The most serious issue in cross-language porting is the absence of reference annotations in the target language; thus, crowd quality control and the evaluation of the collected annotations is difficult. In this paper we investigate targeted crowdsourcing for semantic annotation transfer that delegates to crowds a complex task such as segmenting and labeling of concepts taken from a domain ontology; and evaluation using source language annotation. To test the applicability and effectiveness of the crowdsourced annotation transfer we have considered the case of close and distant language pairs: Italian–Spanish and Italian–Greek. The corpora annotated via crowdsourcing are evaluated against source and target language expert annotations. We demonstrate that the two evaluation references (source and target) highly correlate with each other; thus, drastically reduce the need for the target language reference annotations.
},
keywords = {Signal Annotation and Interpretation}
}

@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{S.2014,
title = {Comparing Stochastic Approaches to Spoken Language Understanding in Multiple Languages},
author = {Han S., Dinarelli M., Raymond C., Lefevre F., Lehnen P., De Mori R., Moschitti A., Ney H. and Riccardi G.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/IEEETSLP10-MultSLU.pdf},
year = {2014},
date = {2014-01-01},
journal = {IEEE Trans. on Audio, Speech and Language Processing, vol. 19, no. 6, pp. 1569-1583, 2011},
abstract = {One of the first steps in building a spoken language understanding (SLU) module for dialogue systems is the extraction of flat concepts out of a given word sequence, usually provided by an automatic speech recognition (ASR) system. In this paper, six different modeling approaches are investigated to tackle the task of concept tagging. These methods include classical, well-known generative and discriminative methods like Finite State Transducers (FSTs), Statistical Machine Translation (SMT), Maximum Entropy Markov Models (MEMMs), or Support Vector Machines (SVMs) as well as techniques recently applied to natural language processing such as Conditional Random Fields (CRFs) or Dynamic Bayesian Networks (DBNs). Following a detailed description of the models, experimental and comparative results are presented on three corpora in different languages and with different complexity. The French MEDIA corpus has already been exploited during an evaluation campaign and so a direct comparison with existing benchmarks is possible. Recently collected Italian and Polish corpora are used to test the robustness and portability of the modeling approaches. For all tasks, manual transcriptions as well as ASR inputs are considered. Additionally to single systems, methods for system combination are investigated. The best performing model on all tasks is based on conditional random fields. On the MEDIA evaluation corpus, a concept error rate of 12.6% could be achieved. Here, additionally to attribute names, attribute values have been extracted using a combination of a rule-based and a statistical approach. Applying system combination using weighted ROVER with all six systems, the concept error rate (CER) drops to 12.0%.},
keywords = {Signal Annotation and Interpretation, Speech Processing}
}

@article{M.2012,
title = {Discriminative Reranking for Spoken Language Understanding},
author = {Dinarelli M., Moschitti A. and Riccardi G.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/IEEETSLP11-DRMSLU1.pdf},
year = {2012},
date = {2012-01-01},
journal = {IEEE Trans. on Audio, Speech and Language Processing, vol. 20, no. 2, pp. 526-539, 2012},
abstract = {Spoken language understanding (SLU) is concerned with the extraction of meaning structures from spoken utterances. Recent computational approaches to SLU, e.g., conditional random fields (CRFs), optimize local models by encoding several features, mainly based on simple n-grams. In contrast, recent works have shown that the accuracy of CRF can be significantly improved by modeling long-distance dependency features. In this paper, we propose novel approaches to encode all possible dependencies between features and most importantly among parts of the meaning structure, e.g., concepts and their combination. We rerank hypotheses generated by local models, e.g., stochastic finite state transducers (SFSTs) or CRF, with a global model. The latter encodes a very large number of dependencies (in the form of trees or sequences) by applying kernel methods to the space of all meaning (sub) structures. We performed comparative experiments between SFST, CRF, support vector machines (SVMs), and our proposed discriminative reranking models (DRMs) on representative conversational speech corpora in three different languages: the ATIS (English), the MEDIA (French), and the LUNA (Italian) corpora. These corpora have been collected within three different domain applications of increasing complexity: informational, transactional, and problem-solving tasks, respectively. The results show that our DRMs consistently outperform the state-of-the-art models based on CRF.},
keywords = {Signal Annotation and Interpretation, 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}
}