35 citations · 68 across the 9 of their papers we have counts for
9 papers
Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing Jailbreaks
Tian Gao, Zhipeng Xie, Yuhao Wu +2
Open-weight large language models face a low-cost white-box threat from representation engineering attacks. Attackers can estimate refusal directions and search for projection-matr…
Beyond Speech: Dual-Domain SSL Fusion for Unified All-Type Audio Deepfake Detection
Cunhang Fan, Junqin Cao, Tian Gao +4
Unified all-type audio deepfake detection aims to determine whether an input clip is real or fake when its audio type may be speech, environmental sound, singing voice, or music. E…
AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer
Kang Li, Yan Song, Li-Rong Dai +3
In this paper, we propose an effective sound event detection (SED) method based on the audio spectrogram transformer (AST) model, pretrained on the large-scale AudioSet for audio t…
A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition
Ye-Qian Du, Jie Zhang, Qiu-Shi Zhu +4
Unpaired data has shown to be beneficial for low-resource automatic speech recognition~(ASR), which can be involved in the design of hybrid models with multi-task training or langu…
Learning Contextually Fused Audio-visual Representations for Audio-visual Speech Recognition
Zi-Qiang Zhang, Jie Zhang, Jian-Shu Zhang +3
With the advance in self-supervised learning for audio and visual modalities, it has become possible to learn a robust audio-visual speech representation. This would be beneficial…
A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognition
Qiu-Shi Zhu, Jie Zhang, Zi-Qiang Zhang +3
Wav2vec2.0 is a popular self-supervised pre-training framework for learning speech representations in the context of automatic speech recognition (ASR). It was shown that wav2vec2.…
USTC-NELSLIP System Description for DIHARD-III Challenge
Yuxuan Wang, Maokui He, Shutong Niu +6
This system description describes our submission system to the Third DIHARD Speech Diarization Challenge. Besides the traditional clustering based system, the innovation of our sys…
XLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech Recognition
Zi-Qiang Zhang, Yan Song, Ming-Hui Wu +2
In this paper, we propose a weakly supervised multilingual representation learning framework, called cross-lingual self-training (XLST). XLST is able to utilize a small amount of a…
Channel adversarial training for cross-channel text-independent speaker recognition
Xin Fang, Liang Zou, Jin Li +2
The conventional speaker recognition frameworks (e.g., the i-vector and CNN-based approach) have been successfully applied to various tasks when the channel of the enrolment datase…