collaborators

11 papers

cs.SD2026

NVV-SuperBench: Beyond Words, Beyond Quality-Benchmarking Nonverbal Vocalizations in Speech Generation

Liumeng Xue, Weizhen Bian, Jiahao Pan +9

Nonverbal vocalizations (NVVs), such as laughing, sighing, and sobbing, are essential for human-like speech, yet standardized evaluation rarely jointly assesses whether systems gen…

cs.CV2026

Listening Deepfake Detection: A New Perspective Beyond Speaking-Centric Forgery Analysis

Miao Liu, Fangda Wei, Jing Wang +1

Existing deepfake detection research has primarily focused on scenarios where the manipulated subject is actively speaking, i.e., generating fabricated content by altering the spea…

cs.MM2026

EgoAdapt: Enhancing Robustness in Egocentric Interactive Speaker Detection Under Missing Modalities

Xinyuan Qian, Xinjia Zhu, Alessio Brutti +1

TTM (Talking to Me) task is a pivotal component in understanding human social interactions, aiming to determine who is engaged in conversation with the camera-wearer. Traditional m…

eess.AS2026

Beyond Lips: Integrating Gesture and Lip Cues for Robust Audio-visual Speaker Extraction

Zexu Pan, Xinyuan Qian, Shengkui Zhao +2

Most audio-visual speaker extraction methods rely on synchronized lip recording to isolate the speech of a target speaker from a multi-talker mixture. However, in natural human com…

cs.SD2026

Analytic Incremental Learning For Sound Source Localization With Imbalance Rectification

Zexia Fan, Yu Chen, Qiquan Zhang +2

Sound source localization (SSL) demonstrates remarkable results in controlled settings but struggles in real-world deployment due to dual imbalance challenges: intra-task imbalance…

eess.AS2025

PerformSinger: Multimodal Singing Voice Synthesis Leveraging Synchronized Lip Cues from Singing Performance Videos

Ke Gu, Zhicong Wu, Peng Bai +5

Existing singing voice synthesis (SVS) models largely rely on fine-grained, phoneme-level durations, which limits their practical application. These methods overlook the complement…