相关论文: M3SD: Multi-modal, Multi-scenario and Multi-langua…

With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…

Many datasets have been designed to further the development of fake audio detection. However, fake utterances in previous datasets are mostly generated by altering timbre, prosody, linguistic content or channel noise of original audio.…

Audio-visual learning has demonstrated promising results in many classical speech tasks (e.g., speech separation, automatic speech recognition, wake-word spotting). We believe that introducing visual modality will also benefit speaker…

Spoken Dialogue Models (SDMs) have recently attracted significant attention for their ability to generate voice responses directly to users' spoken queries. Despite their increasing popularity, there exists a gap in research focused on…

In hours-long meeting scenarios, real-time speech stream often struggles with achieving accurate speaker diarization, commonly leading to speaker identification and speaker count errors. To address this challenge, we propose SCDiar, a…

Speaker diarization systems segment a conversation recording based on the speakers' identity. Such systems can misclassify the speaker of a portion of audio due to a variety of factors, such as speech pattern variation, background noise,…

Speaker diarization may be difficult to achieve when applied to narrative films, where speakers usually talk in adverse acoustic conditions: background music, sound effects, wide variations in intonation may hide the inter-speaker…

Target speaker extraction, which aims at extracting a target speaker's voice from a mixture of voices using audio, visual or locational clues, has received much interest. Recently an audio-visual target speaker extraction has been proposed…

Deep neural networks have recently led to promising results for the task of multiple sound source localization. Yet, they require a lot of training data to cover a variety of acoustic conditions and microphone array layouts. One can…

The performance of speaker diarization is strongly affected by its clustering algorithm at the test stage. However, it is known that clustering algorithms are sensitive to random noises and small variations, particularly when the clustering…

Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial…

In recent years, audio-driven 3D facial animation has gained significant attention, particularly in applications such as virtual reality, gaming, and video conferencing. However, accurately modeling the intricate and subtle dynamics of…

In the rapidly evolving digital era, there is an increasing demand for concise information as individuals seek to distil key insights from various sources. Recent attention from researchers on Multi-document Summarisation (MDS) has resulted…

Fake speech detection systems have become a necessity to combat against speech deepfakes. Current systems exhibit poor generalizability on out-of-domain speech samples due to lack to diverse training data. In this paper, we attempt to…

Synthesizing high-quality 3D face models from natural language descriptions is very valuable for many applications, including avatar creation, virtual reality, and telepresence. However, little research ever tapped into this task. We argue…

We present a novel approach for synthesizing 3D facial motions from audio sequences using key motion embeddings. Despite recent advancements in data-driven techniques, accurately mapping between audio signals and 3D facial meshes remains…

Current movie dubbing technology can produce the desired speech using a reference voice and input video, maintaining perfect synchronization with the visuals while effectively conveying the intended emotions. However, crucial aspects of…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Active speaker detection (ASD) is a multi-modal task that aims to identify who, if anyone, is speaking from a set of candidates. Current audio-visual approaches for ASD typically rely on visually pre-extracted face tracks (sequences of…

We introduce a novel task named `target speech diarization', which seeks to determine `when target event occurred' within an audio signal. We devise a neural architecture called Prompt-driven Target Speech Diarization (PTSD), that works…