This paper analyzes the newest algorithms being used in speech-to-text programs in order to produce the most accurate transcripts possible. Metadata extraction is the main focus, as well as the addition of punctuation prediction. Work was tested on both news speech and conversational speech to produce valid comparisons. Modern applications were also tested to help show where we stand today and ...

Embodied conversational agents (ECAs) have been put forward as a promising means for the training of social skills. The traditional approach to drive the behaviour of ECAs during human-agent dialogues is to use conversation trees. Although this approach is easy to use and very transparent, an important limitation of conversation trees is that the resulting behaviour of the ECAs is often perceiv...

We describe a proposed assistive conversational skills training system using artificial intelligence and natural language generation techniques to simulate spoken dialogue between two embodied agents, one character representing a caregiver and the other character a person with Alzheimer's Disease (AD). The type of dialogue simulated is social conversation in which the caregiver encourages the p...

BACKGROUND Research has shown that children with cerebral palsy have difficulties acquiring communication skills and that conversation with familiar partners follows restricted patterns, which are characterized by high levels of partner control and children's responsivity. Speech and language therapy often includes training for conversational partners to help to them recognize children's commun...

Virtual agents have been used as tools in negotiation—from acting as mediators to manifesting as full-fledged conversational partners. Virtual agents are a powerful tool for teaching negotiation skills, but require an accurate model of human behavior to perform well both as partners and teachers. The work proposed here aims to expand the current horizon of virtual negotiating agents to utilize ...

1. ABSTRACT While seeking a document or information, “some are looking for the ocean and some others for a grain of sand” [5]. We have developed the Halpin1 system to implement our multimodal conversational model for information retrieval. This dialogue-oriented interface allows the access to the INRIA's2 database, on the internet, in a natural language (NL) way, and gives its oral responses vi...

Conversational Case Based Reasoning (CCBR) is a form of CBR where users initiate conversations with the system to solve a certain problem. Current CCBR solutions are limited to specific domains. In the solutions we find a lack of flexibility to deal with the user’s variability: different conversation strategies depending on the user’s current mood, computer skills, and domain expertise. We focu...

The purpose of this study was to train three adolescents with mental handicaps the conversational skills of initiating a topic, and continuing the conversation by cueing an adult listener to speak. A reversal design was used to evaluate the effects of treatment (systematic delay, instruction, prompting, modeling, and reinforcement) on the percentage of functional initiating and cueing behavior ...