相关论文: Face-to-Face: A Video Dataset for Multi-Person Int…

Joint audio-video generation models have shown that unified generation yields stronger cross-modal coherence than cascaded approaches. However, existing models couple modalities throughout denoising via pervasive attention, treating…

Full-duplex voice interaction is crucial for natural human computer interaction. We present a framework that decomposes complex dialogue into minimal conversational units, enabling the system to process each unit independently and predict…

We present a novel approach to any-to-one (A2O) voice conversion (VC) in a sequence-to-sequence (seq2seq) framework. A2O VC aims to convert any speaker, including those unseen during training, to a fixed target speaker. We utilize…

Oral presentation skills are a critical component of higher education, yet comprehensive datasets capturing real-world student performance across multiple modalities remain scarce. To address this gap, we present SOPHIAS (Student Oral…

Talking head synthesis is an emerging technology with wide applications in film dubbing, virtual avatars and online education. Recent NeRF-based methods generate more natural talking videos, as they better capture the 3D structural…

We introduce a novel approach for high-resolution talking head generation from a single image and audio input. Prior methods using explicit face models, like 3D morphable models (3DMM) and facial landmarks, often fall short in generating…

Current diffusion-based text-to-video methods are limited to producing short video clips of a single shot and lack the capability to generate multi-shot videos with discrete transitions where the same character performs distinct activities…

In this work, we propose an ID-preserving talking head generation framework, which advances previous methods in two aspects. First, as opposed to interpolating from sparse flow, we claim that dense landmarks are crucial to achieving…

Video face swapping is becoming increasingly popular across various applications, yet existing methods primarily focus on static images and struggle with video face swapping because of temporal consistency and complex scenarios. In this…

When humans converse, what a speaker will say next significantly depends on what he sees. Unfortunately, existing dialogue models generate dialogue utterances only based on preceding textual contexts, and visual contexts are rarely…

Human face-to-face conversation is an ideal model for human-computer dialogue. One of the major features of face-to-face communication is its multiplicity of communication channels that act on multiple modalities. To realize a natural…

We propose a novel preference alignment framework for improving spoken dialogue models on real-time conversations from user interactions. Current preference learning methods primarily focus on text-based language models, and are not…

Large speech generation models are evolving from single-speaker, short sentence synthesis to multi-speaker, long conversation geneartion. Current long-form speech generation models are predominately constrained to dyadic, turn-based…

Dynamically synthesizing talking speech that actively responds to a listening head is critical during the face-to-face interaction. For example, the speaker could take advantage of the listener's facial expression to adjust the tones,…

Individuals have unique facial expression and head pose styles that reflect their personalized speaking styles. Existing one-shot talking head methods cannot capture such personalized characteristics and therefore fail to produce diverse…

In light of the recent breakthroughs in automatic machine translation systems, we propose a novel approach that we term as "Face-to-Face Translation". As today's digital communication becomes increasingly visual, we argue that there is a…

The generation of stylistic 3D facial animations driven by speech presents a significant challenge as it requires learning a many-to-many mapping between speech, style, and the corresponding natural facial motion. However, existing methods…

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In…

Generating realistic human motions that naturally respond to both spoken language and physical objects is crucial for interactive digital experiences. Current methods, however, address speech-driven gestures or object interactions…

We consider real world task-oriented dialog settings, where agents need to generate both fluent natural language responses and correct external actions like database queries and updates. We demonstrate that, when applied to customer support…