@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{A.2020b,
title = {Is This Dialogue Coherent ? Learning From Dialogue Acts and Entities},
author = {Cervone A. and Riccardi G.},
editor = {SIGDial, Idaho*, 2020},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2020/12/SIGDIAL20-DialogueCoherence.pdf},
year = {2020},
date = {2020-06-01},
keywords = {Conversational and Interactive Systems , Discourse, Natural Language Processing}
}

@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{D.2014,
title = {A Domain-Independent Statistical Methodology for Dialog Management in Spoken Dialog Systems},
author = {Griol D., Callejas Z., Lopez-Cozar R. and Riccardi G.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/CSL14-StatisticalDialogueManager1.pdf},
year = {2014},
date = {2014-01-01},
journal = {Computer Speech and Language, to be published in 2014},
abstract = {This paper proposes a domain-independent statistical methodology to develop dialog managers for spoken dialog systems. Our methodology employs a data-driven classification procedure to generate abstract representations of system turns taking into account the previous history of the dialog. A statistical framework is also introduced for the development and evaluation of dialog systems created using the methodology, which is based on a dialog simulation technique. The benefits and flexibility of the proposed methodology have been validated by developing statistical dialog managers for four spoken dialog systems of different complexity, designed for different languages (English, Italian, and Spanish) and application domains (from transactional to problem-solving tasks). The evaluation results show that the proposed methodology allows rapid development of new dialog managers as well as to explore new dialog strategies, which permit developing new enhanced versions of already existing systems. © 2013 Elsevier Ltd. All rights reserved.},
keywords = {Conversational and Interactive Systems , 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{Riccardi2005,
title = {Grounding Emotions in Human-Machine Conversational Systems},
author = {Riccardi G. and Hakkani-Tur D.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/intetain05.pdf},
year = {2005},
date = {2005-01-01},
journal = {Lecture Notes in Computer Science, Springer-Verlag, , pp. 144 – 154, 2005},
abstract = {Abstract. In this paper we investigate the role of user emotions in human-machine goal-oriented conversations. There has been a growing interest in predicting emotions from acted and non-acted spontaneous speech. Much of the research work has gone in determining what are the correct labels and improving emotion prediction accuracy. In this paper we evaluate the value of user emotional state towards a computational model of emotion processing. We consider a binary representation of emotions (positive vs. negative) in the context of a goal-driven conversational system. For each human-machine interaction we acquire the temporal emotion sequence going from the initial to the final conversational state. These traces are used as features to characterize the user state dynamics. We ground the emotion traces by associating its patterns to dialog strategies and their effectiveness. In order to quantify the value of emotion indicators, we evaluate their predictions in terms of speech recognition and spoken language understanding errors as well as task success or failure. We report results on the 11.5K dialog corpus samples from the How may I Help You? corpus.},
keywords = {Affective Computing, Conversational and Interactive Systems }
}

@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{A2002,
title = {Automated Natural Spoken Dialog},
author = {Gorin A., Abella A., Alonso T., Riccardi G. and Wright J.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/computer_magazine_2002.pdf},
year = {2002},
date = {2002-01-01},
journal = {IEEE Computer, vol. 35, n.4, pp. 51-56, April, 2002 (invited paper)},
abstract = {Engineers have long sought to design systems that understand and act upon spoken language. Extracting meaning from natural, unconstrained speech over the telephone is technically challenging, and quantifying semantic content is crucial for engineering and evaluating such systems.},
keywords = {Conversational and Interactive Systems , Speech Processing}
}

@article{Riccardi2000,
title = {Spoken language adaptation over time and state in a natural spoken dialog system},
author = {Riccardi G. and Gorin A. L.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/IEEETSLP00-LMAdapt.pdf},
year = {2000},
date = {2000-01-01},
journal = {IEEE Trans. on Speech and Audio, vol. 8, pp. 3-10, 2000},
abstract = {We are interested in adaptive spoken dialog systems for automated services. Peoples’ spoken language usage varies over time for a given task, and furthermore varies depending on the state of the dialog. Thus, it is crucial to adapt automatic speech recognition (ASR) language models to these varying conditions. We characterize and quantify these variations based on a database of 30K user-transactions with AT&T’s experimental How May I Help You? spoken dialog system. We describe a novel adaptation algorithm for language models with time and dialog-state varying parameters. Our language adaptation framework allows for recognizing and understanding unconstrained speech at each stage of the dialog, enabling context-switching and error recovery. These models have been used to train state-dependent ASR language models. We have evaluated their performance with respect to word accuracy and perplexity over time and dialog states. We have achieved a reduction of 40% in perplexity and of 8.4% in word error rate over the baseline system, averaged across all dialog states.},
keywords = {Conversational and Interactive Systems , Language Modeling, Speech Processing}
}

@article{Arai1999,
title = {Grammar fragment acquisition using syntactic and semantic clustering},
author = {Arai K., Wright J. H., Riccardi G. and Gorin A. L.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/fragclustering-speechcomm-19981.pdf},
year = {1999},
date = {1999-01-01},
journal = {Speech Communication, vol. 27, no. 1, Jan. 1999},
abstract = {A new method for automatically acquiring Fragments for understanding ̄uent speech is proposed. The goal of this method is to generate a collection of Fragments, each representing a set of syntactically and semantically similar phrases. First, phrases observed frequently in the training set are selected as candidates. Each candidate phrase has three associated probability distributions: of following contexts, of preceding contexts, and of associated semantic actions. The similarity between candidate phrases is measured by applying the Kullback±Leibler distance to these three probability distributions. Candidate phrases that are close in all three distances are clustered into a Fragment. Salient sequences of these Fragments are then automatically acquired, and exploited by a spoken language understanding module to classify calls in AT&T\'s ``How may I help you?\'\' task. These Fragments allow us to generalize unobserved phrases. For instance, they detected 246 phrases in the test-set that were not present in the training-set. This result shows that unseen phrases can be automatically discovered by our new method. Experimental results show that 2.8% of the improvement in call-type classi®catio},
keywords = {Conversational and Interactive Systems , Language Modeling, Speech Processing}
}

@article{Gorin1997,
title = {How may I help you?},
author = {Gorin A. L., Riccardi G. and Wright J. H.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/specom97.pdf},
year = {1997},
date = {1997-01-01},
journal = {Speech Communication, vol. 23, Oct. 1997, pp. 113-127.},
abstract = {We are interested in providing automated services via natural spoken dialog systems. By natural, we mean that the machine understands and acts upon what people actually say, in contrast to what one would like them to say. There are many issues that arise when such systems are targeted for large populations of non-expert users. In this paper, we focus on the task of automatically routing telephone calls based on a user’s fluently spoken response to the open-ended prompt of ‘‘How may I help you?’’. We first describe a database generated from 10,000 spoken transactions between customers and human agents. We then describe methods for automatically acquiring language models for both recognition and understanding from such data. Experimental results evaluating call-classification from speech are reported for that database. These methods have been embedded within a spoken dialog system, with subsequent processing for information retrieval and formfilling. q 1997 Elsevier Science B.V.},
keywords = {Conversational and Interactive Systems , Speech Processing}
}

@article{Riccardi1996,
title = {Stochastic automata for language modeling},
author = {Riccardi G., Pieraccini R. and Bocchieri E.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/csl96.pdf},
year = {1996},
date = {1996-01-01},
journal = { Computer Speech and Language, vol. 10(4), 1996, pp. 265-293},
abstract = {Stochastic language models are widely used in spoken language understanding to recognize and interpret the speech signal: the speech samples are decoded into word transcriptions by means of acoustic and syntactic models and then interpreted according to a semantic model. Both for speech recognition and understanding, search algorithms use stochastic models to extract the most likely uttered sentence and its correspondent interpretation. The design of the language models has to be effective in order to mostly constrain the search algorithms and has to be efficient to comply with the storage space limits. In this work we present the Variable N-gram Stochastic Automaton (VNSA) language model that provides a unified formalism for building a wide class of language models. First, this approach allows for the use of accurate language models for large vocabulary speech recognition by using the standard search algorithm in the one-pass Viterbi decoder. Second, the unified formalism is an effective approach to incorporate different sources of information for computing the probability of word sequences. Third, the VNSAs are well suited for those applications where speech and language decoding cascades are implemented through weighted rational transductions. The VNSAs have been compared to standard bigram and trigram language models and their reduced set of parameters does not affect by any means the performances in terms of perplexity. The design of a stochastic language model through the VNSA is described and applied to word and phrase class-based language models. The effectiveness of VNSAs has been tested within the Air Travel Information System (ATIS) task to build the language model for th},
keywords = {Conversational and Interactive Systems , Language Modeling, Speech Processing}
}