Related papers: Retrieval-Augmented Dialogue Knowledge Aggregation…
Retrieval-Augmented Generation (RAG) has emerged as an important means of enhancing the performance of large language models (LLMs) in knowledge-intensive tasks. However, most existing RAG strategies treat retrieved passages in a flat and…
Stylized image captioning systems aim to generate a caption not only semantically related to a given image but also consistent with a given style description. One of the biggest challenges with this task is the lack of sufficient paired…
In this work we discuss the related challenges and describe an approach towards the fusion of state-of-the-art technologies from the Spoken Dialogue Systems (SDS) and the Semantic Web and Information Retrieval domains. We envision a…
Conversational Speech Synthesis (CSS) aims to generate speech with natural prosody by understanding the multimodal dialogue history (MDH). The latest work predicts the accurate prosody expression of the target utterance by modeling the…
Retrieval-Augmented Generation (RAG) has significantly enhanced large language models (LLMs) in knowledge-intensive tasks by incorporating external knowledge retrieval. However, existing RAG frameworks primarily rely on semantic similarity…
Constructing responses in task-oriented dialogue systems typically relies on information sources such the current dialogue state or external databases. This paper presents a novel approach to knowledge-grounded response generation that…
Cued Speech (CS) is a visual coding tool to encode spoken languages at the phonetic level, which combines lip-reading and hand gestures to effectively assist communication among people with hearing impairments. The Automatic CS Recognition…
Comparing with traditional text-to-speech (TTS) systems, conversational TTS systems are required to synthesize speeches with proper speaking style confirming to the conversational context. However, state-of-the-art context modeling methods…
Conversational recommender systems (CRSs) capture user preference through textual information in dialogues. However, they suffer from data sparsity on two fronts: the dialogue space is vast and linguistically diverse, while the item space…
Sarcasm detection remains a significant challenge due to its reliance on nuanced contextual understanding, world knowledge, and multi-faceted linguistic cues that vary substantially across different sarcastic expressions. Existing…
In this study, we tackle the challenge of inadequate and costly training data that has hindered the development of conversational question answering (ConvQA) systems. Enterprises have a large corpus of diverse internal documents. Instead of…
Expressive speech synthesis, like audiobook synthesis, is still challenging for style representation learning and prediction. Deriving from reference audio or predicting style tags from text requires a huge amount of labeled data, which is…
Conversational aspect-based sentiment quadruple analysis (DiaASQ) aims to extract the quadruple of target-aspect-opinion-sentiment within a dialogue. In DiaASQ, a quadruple's elements often cross multiple utterances. This situation…
The standardization of clinical data elements (CDEs) aims to ensure consistent and comprehensive patient information across various healthcare systems. Existing methods often falter when standardizing CDEs of varying representation and…
Device-directed speech detection (DDSD) is a binary classification task that separates the user's queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience.…
Recent advances in text-to-speech have significantly improved the expressiveness of synthetic speech. However, a major challenge remains in generating speech that captures the diverse styles exhibited by professional narrators in audiobooks…
Spoken conversational question answering (SCQA) requires machines to model complex dialogue flow given the speech utterances and text corpora. Different from traditional text question answering (QA) tasks, SCQA involves audio signal…
Recent prompt-based text-to-speech (TTS) models can clone an unseen speaker using only a short speech prompt. They leverage a strong in-context ability to mimic the speech prompts, including speaker style, prosody, and emotion. Therefore,…
Speech recognition has of late become a practical technology for real world applications. Aiming at speech-driven text retrieval, which facilitates retrieving information with spoken queries, we propose a method to integrate speech…
Knowledge graph-grounded dialog generation requires retrieving a dialog-relevant subgraph from the given knowledge base graph and integrating it with the dialog history. Previous works typically represent the graph using an external…