Related papers: FlexDuo: A Pluggable System for Enabling Full-Dupl…
This paper introduces a novel approach to Dialogue State Tracking (DST) that leverages Large Language Models (LLMs) to generate natural language descriptions of dialogue states, moving beyond traditional slot-value representations.…
Full-duplex spoken dialogue models (SDMs) can listen and speak simultaneously, enabling interaction dynamics closer to human conversation than turn-based systems. Inspired by neural coupling in human communication, we study how such models…
Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available datasets only include written conversations, which are…
Personalization and contextual coherence are two essential components in building effective persona-grounded dialogue systems. These aspects play a crucial role in enhancing user engagement and ensuring responses are more relevant and…
One of the main bottlenecks in practical full-duplex systems is the oscillator phase noise, which bounds the possible cancellable self-interference power. In this paper, a digitaldomain self-interference cancellation scheme for full-duplex…
Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently mostly through employing reinforcement learning methods. However, these approaches have become very sophisticated. It is time to re-evaluate it.…
Dialog state tracking (DST) is a crucial component in a task-oriented dialog system for conversational information access. A common practice in current dialog systems is to define the dialog state by a set of slot-value pairs. Such…
In this article, we present a real-time full duplex radio system for 5G wireless networks. Full duplex radios are capable of opening new possibilities in contexts of high traffic demand where there are limited radio resources. A critical…
Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language models (LLMs), which are designed to extend a single coherent sequence and do not naturally…
The wireless in-band full-duplex (IBFD) technology can in theory double the system capacity over the conventional frequency division duplex (FDD) or time-division duplex (TDD) alternatives. But the strong self-interference of the IBFD can…
Spoken dialogue generation is crucial for applications like podcasts, dynamic commentary, and entertainment content, but poses significant challenges compared to single-utterance text-to-speech (TTS). Key requirements include accurate…
Recent end-to-end spoken dialogue models enable natural interaction. However, as user demands become increasingly complex, models that rely solely on conversational abilities often struggle to cope. Incorporating agentic capabilities is…
A major focus of recent research in spoken language understanding (SLU) has been on the end-to-end approach where a single model can predict intents directly from speech inputs without intermediate transcripts. However, this approach…
Spoken dialogue models currently lack the ability for fine-grained speech style control, a critical capability for human-like interaction that is often overlooked in favor of purely functional capabilities like reasoning and question…
Proactive dialogues serve as a practical yet challenging dialogue problem in the era of large language models (LLMs), where the dialogue policy planning is the key to improving the proactivity of LLMs. Most existing studies enable the…
In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback…
Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o, have captured significant attention in the speech domain. Compared to traditional three-tier cascaded spoken dialogue models that comprise speech recognition…
While the English virtual assistants have achieved exciting performance with an enormous amount of training resources, the needs of non-English-speakers have not been satisfied well. Up to Dec 2021, Alexa, one of the most popular smart…
Recent works in dialogue state tracking (DST) focus on an open vocabulary-based setting to resolve scalability and generalization issues of the predefined ontology-based approaches. However, they are inefficient in that they predict the…
The full-duplex (FD) communication can achieve higher spectrum efficiency than conventional half-duplex (HD) communication; however, self-interference (SI) is the key hurdle. This paper is the first work to propose the intelligent Omni…