Abstract:Audio-visual Target Speaker Extraction (AV-TSE) aims to isolate the speech of a specific target speaker from an audio mixture using time-synchronized visual cues. In real-world scenarios, visual cues are not always available due to various impairments, which undermines the stability of AV-TSE. Despite this challenge, humans can maintain attentional momentum over time, even when the target speaker is not visible. In this paper, we introduce the Momentum Multi-modal target Speaker Extraction (MoMuSE), which retains a speaker identity momentum in memory, enabling the model to continuously track the target speaker. Designed for real-time inference, MoMuSE extracts the current speech window with guidance from both visual cues and dynamically updated speaker momentum. Experimental results demonstrate that MoMuSE exhibits significant improvement, particularly in scenarios with severe impairment of visual cues.
Abstract:Multimodal Large Language Models have advanced AI in applications like text-to-video generation and visual question answering. These models rely on visual encoders to convert non-text data into vectors, but current encoders either lack semantic alignment or overlook non-salient objects. We propose the Guiding Visual Encoder to Perceive Overlooked Information (GiVE) approach. GiVE enhances visual representation with an Attention-Guided Adapter (AG-Adapter) module and an Object-focused Visual Semantic Learning module. These incorporate three novel loss terms: Object-focused Image-Text Contrast (OITC) loss, Object-focused Image-Image Contrast (OIIC) loss, and Object-focused Image Discrimination (OID) loss, improving object consideration, retrieval accuracy, and comprehensiveness. Our contributions include dynamic visual focus adjustment, novel loss functions to enhance object retrieval, and the Multi-Object Instruction (MOInst) dataset. Experiments show our approach achieves state-of-the-art performance.
Abstract:Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue. We generate a spectral-level representation from the enrollment magnitude spectrogram as a raw, low-level feature, which significantly improves the model's generalization capability. Additionally, we propose a contextual embedding feature based on cross-attention mechanisms that integrate frame-level embeddings from a pre-trained speaker encoder. By incorporating speaker features across multiple levels, we significantly enhance the performance of the TSE model. Our approach achieves a 2.74 dB improvement and a 4.94% increase in extraction accuracy on Libri2mix test set over the baseline.
Abstract:Target speaker extraction (TSE) focuses on isolating the speech of a specific target speaker from overlapped multi-talker speech, which is a typical setup in the cocktail party problem. In recent years, TSE draws increasing attention due to its potential for various applications such as user-customized interfaces and hearing aids, or as a crutial front-end processing technologies for subsequential tasks such as speech recognition and speaker recongtion. However, there are currently few open-source toolkits or available pre-trained models for off-the-shelf usage. In this work, we introduce WeSep, a toolkit designed for research and practical applications in TSE. WeSep is featured with flexible target speaker modeling, scalable data management, effective on-the-fly data simulation, structured recipes and deployment support. The toolkit is publicly avaliable at \url{https://github.com/wenet-e2e/WeSep.}
Abstract:Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms when training data is insufficient, data augmentation is a commonly adopted technique. Unlike typical data augmentation applied to speech mixtures, this work thoroughly investigates the effectiveness of augmenting the enrollment speech space. We found that for both pretrained and jointly optimized speaker encoders, directly augmenting the enrollment speech leads to consistent performance improvement. In addition to conventional methods such as noise and reverberation addition, we propose a novel augmentation method called self-estimated speech augmentation (SSA). Experimental results on the Libri2Mix test set show that our proposed method can achieve an improvement of up to 2.5 dB.
Abstract:We propose a new speech discrete token vocoder, vec2wav 2.0, which advances voice conversion (VC). We use discrete tokens from speech self-supervised models as the content features of source speech, and treat VC as a prompted vocoding task. To amend the loss of speaker timbre in the content tokens, vec2wav 2.0 utilizes the WavLM features to provide strong timbre-dependent information. A novel adaptive Snake activation function is proposed to better incorporate timbre into the waveform reconstruction process. In this way, vec2wav 2.0 learns to alter the speaker timbre appropriately given different reference prompts. Also, no supervised data is required for vec2wav 2.0 to be effectively trained. Experimental results demonstrate that vec2wav 2.0 outperforms all other baselines to a considerable margin in terms of audio quality and speaker similarity in any-to-any VC. Ablation studies verify the effects made by the proposed techniques. Moreover, vec2wav 2.0 achieves competitive cross-lingual VC even only trained on monolingual corpus. Thus, vec2wav 2.0 shows timbre can potentially be manipulated only by speech token vocoders, pushing the frontiers of VC and speech synthesis.
Abstract:Remote sensing shadow removal, which aims to recover contaminated surface information, is tricky since shadows typically display overwhelmingly low illumination intensities. In contrast, the infrared image is robust toward significant light changes, providing visual clues complementary to the visible image. Nevertheless, the existing methods ignore the collaboration between heterogeneous modalities, leading to undesired quality degradation. To fill this gap, we propose a weakly supervised shadow removal network with a spherical feature space, dubbed S2-ShadowNet, to explore the best of both worlds for visible and infrared modalities. Specifically, we employ a modal translation (visible-to-infrared) model to learn the cross-domain mapping, thus generating realistic infrared samples. Then, Swin Transformer is utilized to extract strong representational visible/infrared features. Simultaneously, the extracted features are mapped to the smooth spherical manifold, which alleviates the domain shift through regularization. Well-designed similarity loss and orthogonality loss are embedded into the spherical space, prompting the separation of private visible/infrared features and the alignment of shared visible/infrared features through constraints on both representation content and orientation. Such a manner encourages implicit reciprocity between modalities, thus providing a novel insight into shadow removal. Notably, ground truth is not available in practice, thus S2-ShadowNet is trained by cropping shadow and shadow-free patches from the shadow image itself, avoiding stereotypical and strict pair data acquisition. More importantly, we contribute a large-scale weakly supervised shadow removal benchmark, including 4000 shadow images with corresponding shadow masks.
Abstract:Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature fusion approach has been proposed to effectively capture speaker characteristics from short utterances. Constrained by the model's size, a robust backbone Enhanced Res2Net (ERes2Net) combining global and local feature fusion demonstrates sub-optimal performance in short-duration speaker verification. To further improve the short-duration feature extraction capability of ERes2Net, we expand the channel dimension within each stage. However, this modification also increases the number of model parameters and computational complexity. To alleviate this problem, we propose an improved ERes2NetV2 by pruning redundant structures, ultimately reducing both the model parameters and its computational cost. A range of experiments conducted on the VoxCeleb datasets exhibits the superiority of ERes2NetV2, which achieves EER of 0.61% for the full-duration trial, 0.98% for the 3s-duration trial, and 1.48% for the 2s-duration trial on VoxCeleb1-O, respectively.
Abstract:Search and recommendation (S&R) are the two most important scenarios in e-commerce. The majority of users typically interact with products in S&R scenarios, indicating the need and potential for joint modeling. Traditional multi-scenario models use shared parameters to learn the similarity of multiple tasks, and task-specific parameters to learn the divergence of individual tasks. This coarse-grained modeling approach does not effectively capture the differences between S&R scenarios. Furthermore, this approach does not sufficiently exploit the information across the global label space. These issues can result in the suboptimal performance of multi-scenario models in handling both S&R scenarios. To address these issues, we propose an effective and universal framework for Unified Search and Recommendation (USR), designed with S&R Views User Interest Extractor Layer (IE) and S&R Views Feature Generator Layer (FG) to separately generate user interests and scenario-agnostic feature representations for S&R. Next, we introduce a Global Label Space Multi-Task Layer (GLMT) that uses global labels as supervised signals of auxiliary tasks and jointly models the main task and auxiliary tasks using conditional probability. Extensive experimental evaluations on real-world industrial datasets show that USR can be applied to various multi-scenario models and significantly improve their performance. Online A/B testing also indicates substantial performance gains across multiple metrics. Currently, USR has been successfully deployed in the 7Fresh App.
Abstract: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. However, this strategy mainly focuses on the existence of target speech, while ignoring the variations of the noise characteristics. That may result in extracting noisy signals from the incorrect sound source in challenging acoustic situations. To this end, we propose a novel reverse selective auditory attention mechanism, which can suppress interference speakers and non-speech signals to avoid incorrect speaker extraction. By estimating and utilizing the undesired noisy signal through this mechanism, we design an AV-TSE framework named Subtraction-and-ExtrAction network (SEANet) to suppress the noisy signals. We conduct abundant experiments by re-implementing three popular AV-TSE methods as the baselines and involving nine metrics for evaluation. The experimental results show that our proposed SEANet achieves state-of-the-art results and performs well for all five datasets. We will release the codes, the models and data logs.