This paper presents a dialogue act taxonomy designed for the development of a conversational agent for elderly. The main goal of this conversational agent is to improve life quality of the user by means of coaching sessions in different topics. In contrast to other approaches such as task-oriented dialogue systems and chit-chat implementations, the agent should display a pro-active attitude, driving the conversation to reach a number of diverse coaching goals. Therefore, the main characteristic of the introduced dialogue act taxonomy is its capacity for supporting a communication based on the GROW model for coaching. In addition, the taxonomy has a hierarchical structure between the tags and it is multimodal. We use the taxonomy to annotate a Spanish dialogue corpus collected from a group of elder people. We also present a preliminary examination of the annotated corpus and discuss on the multiple possibilities it presents for further research.

Designing human–machine interactive systems requires cooperation between different disciplines is required. In this work, we present a Dialogue Manager and a Language Generator that are the core modules of a Voice-based Spoken Dialogue System (SDS) capable of carrying out challenging, long and complex coaching conversations. We also develop an efficient integration procedure of the whole system that will act as an intelligent and robust Virtual Coach. The coaching task significantly differs from the classical applications of SDSs, resulting in a much higher degree of complexity and difficulty. The Virtual Coach has been successfully tested and validated in a user study with independent elderly, in three different countries with three different languages and cultures: Spain, France and Norway.

Following the success of Natural Language Processing (NLP) transformers pretrained via self-supervised learning, similar models have been proposed recently for speech processing such as Wav2Vec2, HuBERT and UniSpeech-SAT. An interesting yet unexplored area of application of these models is Spoken Dialogue Systems, where the users' audio signals are typically just mapped to word-level features derived from an Automatic Speech Recogniser (ASR), and then processed using NLP techniques to generate system responses. This paper reports a comprehensive comparison of dialogue policies trained using ASR-based transcriptions and extended with the aforementioned audio processing transformers in the DSTC2 task. Whilst our dialogue policies are trained with supervised and policy-based deep reinforcement learning, they are assessed using both automatic task completion metrics and a human evaluation. Our results reveal that using audio embeddings is more beneficial than detrimental in most of our trained dialogue policies, and that the benefits are stronger for supervised learning than reinforcement learning.

In this work we develop a fully data driven conversational agent capable of carrying out motivational coaching sessions in Spanish, French, Norwegian, and English. Unlike the majority of coaching, and in general well-being related conversational agents that can be found in the literature, ours is not designed by hand-crafted rules. Instead, we directly model the coaching strategy of professionals with end users. To this end, we gather a set of virtual coaching sessions through a Wizard of Oz platform, and apply state of the art Natural Language Processing techniques. We employ a transfer learning approach, pretraining GPT2 neural language models and fine-tuning them on our corpus. However, since these only take as input a local dialogue history, a simple fine-tuning procedure is not capable of modeling the long-term dialogue strategies that appear in coaching sessions. To alleviate this issue, we first propose to learn dialogue phase and scenario embeddings in the fine-tuning stage. These indicate to the model at which part of the dialogue it is and which kind of coaching session it is carrying out. Second, we develop a global deep learning system which controls the long-term structure of the dialogue. We also show that this global module can be used to visualize and interpret the decisions taken by the the conversational agent, and that the learnt representations are comparable to dialogue acts. Automatic and human evaluation show that our proposals serve to improve the baseline models. Finally, interaction experiments with coaching experts indicate that the system is usable and gives rise to positive emotions in Spanish, French and English, while the results in Norwegian point out that there is still work to be done in fully data driven approaches with very low resource languages.

In this work, we present an approach to understand the computational methods and decision-making involved in the identification of emotions in spontaneous speech. The selected task consists of Spanish TV debates, which entail a high level of complexity as well as additional subjectivity in the human perception-based annotation procedure. A simple convolutional neural model is proposed, and its behaviour is analysed to explain its decision-making. The proposed model slightly outperforms commonly used CNN architectures such as VGG16, while being much lighter. Internal layer-by-layer transformations of the input spectrogram are visualised and analysed. Finally, a class model visualisation is proposed as a simple interpretation approach whose usefulness is assessed in the work.