Related papers: PLACES: Prompting Language Models for Social Conve…
The development of natural language processing algorithms and the explosive growth of conversational data are encouraging researches on the human-computer conversation. Still, getting qualified conversational data on a large scale is…
Dialogue state tracking plays a crucial role in extracting information in task-oriented dialogue systems. However, preceding research are limited to textual modalities, primarily due to the shortage of authentic human audio datasets. We…
Prompting is a mainstream paradigm for adapting large language models to specific natural language processing tasks without modifying internal parameters. Therefore, detailed supplementary knowledge needs to be integrated into external…
This paper provides preliminary results on exploring the task of performing turn-level data augmentation for dialogue system based on different types of commonsense relationships, and the automatic evaluation of the generated synthetic…
As the phonetic and acoustic manifestations of laughter in conversation are highly diverse, laughter synthesis should be capable of accommodating such diversity while maintaining high controllability. This paper proposes a generative model…
The future of conversational agents will provide users with personalized information responses. However, a significant challenge in developing models is the lack of large-scale dialogue datasets that span multiple sessions and reflect…
Despite growing interest in applications based on natural customer support conversations, there exist remarkably few publicly available datasets that reflect the expected characteristics of conversations in these settings. Existing…
Using a text description as prompt to guide the generation of text or images (e.g., GPT-3 or DALLE-2) has drawn wide attention recently. Beyond text and image generation, in this work, we explore the possibility of utilizing text…
High-quality speech dialogue datasets are crucial for Speech-LLM development, yet existing acquisition methods face significant limitations. Human recordings incur high costs and privacy concerns, while synthetic approaches often lack…
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…
The emergence of synthetic data represents a pivotal shift in modern machine learning, offering a solution to satisfy the need for large volumes of data in domains where real data is scarce, highly private, or difficult to obtain. We…
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. Dialogue systems are increasingly being designed to move beyond just imitating conversation and also…
Large Language models (LLMs), while powerful, exhibit harmful social biases. Debiasing is often challenging due to computational costs, data constraints, and potential degradation of multi-task language capabilities. This work introduces a…
Artificial Intelligence (AI) advancement is heavily dependent on access to large-scale, high-quality training data. However, in specialized domains such as healthcare, data acquisition faces significant constraints due to privacy…
The increasing capability of Large Language Models to act as human-like social agents raises two important questions in the area of opinion dynamics. First, whether these agents can generate effective arguments that could be injected into…
We present a novel end-to-end personality-based synthetic dialogue data generation pipeline, specifically designed to elicit responses from large language models via prompting. We design the prompts to generate more human-like dialogues…
Enhancing user engagement through personalization in conversational agents has gained significance, especially with the advent of large language models that generate fluent responses. Personalized dialogue generation, however, is…
Spontaneous style speech synthesis, which aims to generate human-like speech, often encounters challenges due to the scarcity of high-quality data and limitations in model capabilities. Recent language model-based TTS systems can be trained…
This report characterized the suitability of existing datasets for devising new Machine Learning models, decision making methods, and analysis algorithms to improve Collaborative Problem Solving and then enumerated requirements for future…
This study investigated the effect of synthetic voice of conversational agent trained with spontaneous speech on human interactants. Specifically, we hypothesized that humans will exhibit more social responses when interacting with…