中文
相关论文

相关论文: AVFSNet: Audio-Visual Speech Separation for Flexib…

200 篇论文

The scarcity of labeled audio-visual datasets is a constraint for training superior audio-visual speaker diarization systems. To improve the performance of audio-visual speaker diarization, we leverage pre-trained supervised and…

音频与语音处理 · 电气工程与系统科学 2023-12-08 Huan Zhao , Li Zhang , Yue Li , Yannan Wang , Hongji Wang , Wei Rao , Qing Wang , Lei Xie

Audio-visual target speaker extraction (AV-TSE) aims to extract the specific person's speech from the audio mixture given auxiliary visual cues. Previous methods usually search for the target voice through speech-lip synchronization.…

音频与语音处理 · 电气工程与系统科学 2025-03-04 Ruijie Tao , Xinyuan Qian , Yidi Jiang , Junjie Li , Jiadong Wang , Haizhou Li

Audio-Visual Target Speaker Extraction (AVTSE) aims to isolate a target speaker's voice in a multi-speaker environment with visual cues as auxiliary. Most of the existing AVTSE methods encode visual and audio features simultaneously,…

声音 · 计算机科学 2025-11-13 Zixuan Li , Xueliang Zhang , Lei Miao , Zhipeng Yan , Ying Sun , Chong Zhu

We propose Audio-Visual Lightweight ITerative model (AVLIT), an effective and lightweight neural network that uses Progressive Learning (PL) to perform audio-visual speech separation in noisy environments. To this end, we adopt the…

音频与语音处理 · 电气工程与系统科学 2023-06-02 Héctor Martel , Julius Richter , Kai Li , Xiaolin Hu , Timo Gerkmann

The framework of visually-guided sound source separation generally consists of three parts: visual feature extraction, multimodal feature fusion, and sound signal processing. An ongoing trend in this field has been to tailor involved visual…

声音 · 计算机科学 2023-06-21 Zengjie Song , Zhaoxiang Zhang

This paper addresses the challenge of audio-visual single-microphone speech separation and enhancement in the presence of real-world environmental noise. Our approach is based on generative inverse sampling, where we model clean speech and…

音频与语音处理 · 电气工程与系统科学 2026-02-03 Yochai Yemini , Yoav Ellinson , Rami Ben-Ari , Sharon Gannot , Ethan Fetaya

Our goal is to isolate individual speakers from multi-talker simultaneous speech in videos. Existing works in this area have focussed on trying to separate utterances from known speakers in controlled environments. In this paper, we propose…

计算机视觉与模式识别 · 计算机科学 2018-06-20 Triantafyllos Afouras , Joon Son Chung , Andrew Zisserman

Single-channel, speaker-independent speech separation methods have recently seen great progress. However, the accuracy, latency, and computational cost of such methods remain insufficient. The majority of the previous methods have…

声音 · 计算机科学 2019-05-16 Yi Luo , Nima Mesgarani

Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the…

音频与语音处理 · 电气工程与系统科学 2024-01-09 Qiushi Zhu , Jie Zhang , Yu Gu , Yuchen Hu , Lirong Dai

The Audio-Visual Speaker Extraction (AVSE) algorithm employs parallel video recording to leverage two visual cues, namely speaker identity and synchronization, to enhance performance compared to audio-only algorithms. However, the visual…

声音 · 计算机科学 2023-06-06 Junjie Li , Meng Ge , Zexu pan , Rui Cao , Longbiao Wang , Jianwu Dang , Shiliang Zhang

Speech separation has been extensively studied to deal with the cocktail party problem in recent years. All related approaches can be divided into two categories: time-frequency domain methods and time domain methods. In addition, some…

音频与语音处理 · 电气工程与系统科学 2022-03-31 Fan-Lin Wang , Yu-Huai Peng , Hung-Shin Lee , Hsin-Min Wang

The practical deployment of Audio-Visual Speech Recognition (AVSR) systems is fundamentally challenged by significant performance degradation in real-world environments, characterized by unpredictable acoustic noise and visual interference.…

音频与语音处理 · 电气工程与系统科学 2025-12-17 Sungnyun Kim

In this paper, we propose long short term memory speech enhancement network (LSTMSE-Net), an audio-visual speech enhancement (AVSE) method. This innovative method leverages the complementary nature of visual and audio information to boost…

Audio-visual automatic speech recognition is a promising approach to robust ASR under noisy conditions. However, up until recently it had been traditionally studied in isolation assuming the video of a single speaking face matches the…

音频与语音处理 · 电气工程与系统科学 2022-05-13 Otavio Braga , Olivier Siohan

Recent studies have demonstrated that incorporating auxiliary information, such as speaker voiceprint or visual cues, can substantially improve Speech Enhancement (SE) performance. However, single-channel methods often yield suboptimal…

音频与语音处理 · 电气工程与系统科学 2026-03-06 Chihyun Liu , Jiaxuan Fan , Mingtung Sun , Michael Anthony , Mingsian R. Bai , Yu Tsao

Robust speech processing in multi-talker environments requires effective speech separation. Recent deep learning systems have made significant progress toward solving this problem, yet it remains challenging particularly in real-time, short…

声音 · 计算机科学 2018-04-19 Yi Luo , Nima Mesgarani

Audio-visual approaches involving visual inputs have laid the foundation for recent progress in speech separation. However, the optimization of the concurrent usage of auditory and visual inputs is still an active research area. Inspired by…

声音 · 计算机科学 2024-03-26 Kai Li , Fenghua Xie , Hang Chen , Kexin Yuan , Xiaolin Hu

Audio-visual speaker tracking aims to determine the location of human targets in a scene using signals captured by a multi-sensor platform, whose accuracy and robustness can be improved by multi-modal fusion methods. Recently, several…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Yidi Li , Hong Liu , Bing Yang

We present a unified network for voice separation of an unknown number of speakers. The proposed approach is composed of several separation heads optimized together with a speaker classification branch. The separation is carried out in the…

声音 · 计算机科学 2020-11-05 Shlomo E. Chazan , Lior Wolf , Eliya Nachmani , Yossi Adi

Target speech separation refers to isolating target speech from a multi-speaker mixture signal by conditioning on auxiliary information about the target speaker. Different from the mainstream audio-visual approaches which usually require…

音频与语音处理 · 电气工程与系统科学 2020-05-19 Leyuan Qu , Cornelius Weber , Stefan Wermter