相关论文: Push-Pull: Characterizing the Adversarial Robustne…

Vision-language pre-training (VLP) models, trained on large-scale image-text pairs, have become widely used across a variety of downstream vision-and-language (V+L) tasks. This widespread adoption raises concerns about their vulnerability…

As Large Language Models make a breakthrough in natural language processing tasks (NLP), multimodal technique becomes extremely popular. However, it has been shown that multimodal NLP are vulnerable to adversarial attacks, where the outputs…

Audiovisual active speaker detection (ASD) addresses the task of determining the speech activity of a candidate speaker given acoustic and visual data. Typically, systems model the temporal correspondence of audiovisual cues, such as the…

Concurrent Speaker Detection (CSD), the task of identifying active speakers and their overlaps in an audio signal, is essential for various audio applications, including meeting transcription, speaker diarization, and speech separation.…

The Multi-modal Information based Speech Processing (MISP) challenge aims to extend the application of signal processing technology in specific scenarios by promoting the research into wake-up words, speaker diarization, speech recognition,…

Audio-visual speech recognition (AVSR) provides a promising solution to ameliorate the noise-robustness of audio-only speech recognition with visual information. However, most existing efforts still focus on audio modality to improve…

Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to detect the presence of adversarial examples, i.e., a binary…

Separating target speech from mixed signals containing flexible speaker quantities presents a challenging task. While existing methods demonstrate strong separation performance and noise robustness, they predominantly assume prior knowledge…

Conventional audio-visual approaches for active speaker detection (ASD) typically rely on visually pre-extracted face tracks and the corresponding single-channel audio to find the speaker in a video. Therefore, they tend to fail every time…

We present an approach to Audio-Visual Speech Recognition that builds on a pre-trained Whisper model. To infuse visual information into this audio-only model, we extend it with an AV fusion module and LoRa adapters, one of the most…

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…

The Audio-Visual Event Localization (AVEL) task aims to temporally locate and classify video events that are both audible and visible. Most research in this field assumes a closed-set setting, which restricts these models' ability to handle…

Recent studies in multi-agent communicative reinforcement learning (MACRL) have demonstrated that multi-agent coordination can be greatly improved by allowing communication between agents. Meanwhile, adversarial machine learning (ML) has…

Reward function specification, which requires considerable human effort and iteration, remains a major impediment for learning behaviors through deep reinforcement learning. In contrast, providing visual demonstrations of desired behaviors…

Learning a good speaker embedding is important for many automatic speaker recognition tasks, including verification, identification and diarization. The embeddings learned by softmax are not discriminative enough for open-set verification…

Audio-visual speech contains synchronized audio and visual information that provides cross-modal supervision to learn representations for both automatic speech recognition (ASR) and visual speech recognition (VSR). We introduce continuous…

With recent advances in autonomous driving, Voice Control Systems have become increasingly adopted as human-vehicle interaction methods. This technology enables drivers to use voice commands to control the vehicle and will be soon available…

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

Audio-Visual Source Localization (AVSL) aims to localize the source of sound within a video. In this paper, we identify a significant issue in existing benchmarks: the sounding objects are often easily recognized based solely on visual…

Automatic speech recognition (ASR) systems have been shown to be vulnerable to adversarial examples (AEs). Recent success all assumes that users will not notice or disrupt the attack process despite the existence of music/noise-like sounds…