Related papers: Why Are Conversational Assistants Still Black Boxe…
Though recommender systems are defined by personalization, recent work has shown the importance of additional, beyond-accuracy objectives, such as fairness. Because users often expect their recommendations to be purely personalized, these…
People with special needs like blind and visually impaired (BVI) people can particularly benefit from using voice assistants providing spoken information input and output in everyday life. However, it is crucial to understand their needs…
Conversational AI interfaces powered by large language models (LLMs) are increasingly used as coding assistants. However, questions remain about how programmers interact with LLM-based conversational agents, the challenges they encounter,…
Smart speakers and voice-based virtual assistants are core components for the success of the IoT paradigm. Unfortunately, they are vulnerable to various privacy threats exploiting machine learning to analyze the generated encrypted traffic.…
Concerns about the risks and harms posed by artificial intelligence (AI) have resulted in significant study into algorithmic transparency, giving rise to a sub-field known as Explainable AI (XAI). Unfortunately, despite a decade of…
Voice control in the smart home is commonplace, enabling the convenient control of smart home Internet of Things hubs, gateways and devices, along with information seeking dialogues. Cloud-based voice assistants are used to facilitate the…
Online Digital Assistants, such as Amazon Alexa, Google Assistant, Apple Siri are very popular and provide a range or services to their users, a key function is their ability to satisfy user information needs from the sources available to…
Conversational LLMs function as black box systems, leaving users guessing about why they see the output they do. This lack of transparency is potentially problematic, especially given concerns around bias and truthfulness. To address this…
In the age of personal voice assistants, the question of privacy arises. These digital companions often lack memory of past interactions, while relying heavily on the internet for speech processing, raising privacy concerns. Modern…
This study explores the integration of contextual explanations into AI-powered loan decision systems to enhance trust and usability. While traditional AI systems rely heavily on algorithmic transparency and technical accuracy, they often…
Speaker anonymization is the task of modifying a speech recording such that the original speaker cannot be identified anymore. Since the first Voice Privacy Challenge in 2020, along with the release of a framework, the popularity of this…
Transparency is often deemed critical to enable effective real-world deployment of intelligent systems. Yet the motivations for and benefits of different types of transparency can vary significantly depending on context, and objective…
The growing capabilities of large language models and multimodal systems have spurred interest in voice-first AI assistants, yet existing benchmarks are inadequate for evaluating the full range of these systems' capabilities. We introduce…
Open-domain conversational search assistants aim at answering user questions about open topics in a conversational manner. In this paper we show how the Transformer architecture achieves state-of-the-art results in key IR tasks, leveraging…
Intelligent conversational assistants, such as Apple's Siri, Microsoft's Cortana, and Amazon's Echo, have quickly become a part of our digital life. However, these assistants have major limitations, which prevents users from conversing with…
Audio signals can reveal intimate details about a person's life, including their conversations, health status, emotions, location, and personal preferences. Unauthorized access or misuse of this information can have profound personal and…
Anonymisation has the goal of manipulating speech signals in order to degrade the reliability of automatic approaches to speaker recognition, while preserving other aspects of speech, such as those relating to intelligibility and…
In the past decade, the financial industry has experienced a technology revolution. While we witness a rapid introduction of conversational bots for financial services, there is a lack of understanding of conversational user interfaces…
This study presents a unique framework that applies and extends Solove (2006)'s taxonomy to address privacy concerns in interactions with text-based AI chatbots. As chatbot prevalence grows, concerns about user privacy have heightened.…
Using our voices to access, and interact with, online services raises concerns about the trade-offs between convenience, privacy, and security. The conflict between maintaining privacy and ensuring input authenticity has often been hindered…