Related papers: The Manga Whisperer: Automatically Generating Tran…
We propose task-adaptive tokenization as a way to adapt the generation pipeline to the specifics of a downstream task and enhance long-form generation in mental health. Inspired by insights from cognitive science, our task-adaptive…
Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure. Some…
Dialogue authoring in large games requires not only content creation but the subtlety of its delivery, which can vary from character to character. Manually authoring this dialogue can be tedious, time-consuming, or even altogether…
To address the data scarcity issue in Conversational question answering (ConvQA), a dialog inpainting method, which utilizes documents to generate ConvQA datasets, has been proposed. However, the original dialog inpainting model is trained…
Typical methods for evaluating the performance of language models evaluate their ability to answer questions accurately. These evaluation metrics are acceptable for determining the extent to which language models can understand and reason…
This paper provides a proof of concept that audio of tabletop role-playing games (TTRPG) could serve as a challenge for diarization systems. TTRPGs are carried out mostly by conversation. Participants often alter their voices to indicate…
Recent advancements in video generation have achieved impressive motion realism, yet they often overlook character-driven storytelling, a crucial task for automated film, animation generation. We introduce Talking Characters, a more…
We present STUDIES, a new speech corpus for developing a voice agent that can speak in a friendly manner. Humans naturally control their speech prosody to empathize with each other. By incorporating this "empathetic dialogue" behavior into…
Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…
ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by…
Personalized dialogue systems aim to endow the chatbot agent with more anthropomorphic traits for human-like interactions. Previous approaches have explored explicitly user profile modeling using text descriptions, implicit derivation of…
This study investigates innovative interaction designs for communication and collaborative learning between learners of mixed hearing and signing abilities, leveraging advancements in mixed reality technologies like Apple Vision Pro and…
As a popular comic style, manga offers a unique impression by utilizing a rich set of bitonal patterns, or screentones, for illustration. However, screentones can easily be contaminated with visual-unpleasant aliasing and/or blurriness…
Generating metaphors is a challenging task as it requires a proper understanding of abstract concepts, making connections between unrelated concepts, and deviating from the literal meaning. In this paper, we aim to generate a metaphoric…
Multi-talker overlapped speech recognition remains a significant challenge, requiring not only speech recognition but also speaker diarization tasks to be addressed. In this paper, to better address these tasks, we first introduce speaker…
Recent approaches to automatically detect the speaker of an utterance of direct speech often disregard general information about characters in favor of local information found in the context, such as surrounding mentions of entities. In…
Despite significant advancements in natural language generation, controlling language models to produce texts with desired attributes remains a formidable challenge. In this work, we introduce RSA-Control, a training-free controllable text…
We present a novel language adaptable spell checking system which detects spelling errors and suggests context sensitive corrections in real-time. We show that our system can be extended to new languages with minimal language-specific…
Conversational Speech Synthesis (CSS) aims to align synthesized speech with the emotional and stylistic context of user-agent interactions to achieve empathy. Current generative CSS models face interpretability limitations due to…
In the landscape of modern machine learning, frozen pre-trained models provide stability and efficiency but often underperform on specific tasks due to mismatched data distributions. This paper introduces the Whisperer, a novel visual…