STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking

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 fusion methods have been proposed to model the correlation in multiple modalities. However, for the speaker tracking problem, the cross-modal interaction between audio and visual signals hasn't been well exploited. To this end, we present a novel Speaker Tracking Network (STNet) with a deep audio-visual fusion model in this work. We design a visual-guided acoustic measurement method to fuse heterogeneous cues in a unified localization space, which employs visual observations via a camera model to construct the enhanced acoustic map. For feature fusion, a cross-modal attention module is adopted to jointly model multi-modal contexts and interactions. The correlated information between audio and visual features is further interacted in the fusion model. Moreover, the STNet-based tracker is applied to multi-speaker cases by a quality-aware module, which evaluates the reliability of multi-modal observations to achieve robust tracking in complex scenarios. Experiments on the AV16.3 and CAV3D datasets show that the proposed STNet-based tracker outperforms uni-modal methods and state-of-the-art audio-visual speaker trackers.

RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization

The training of deep learning-based multichannel speech enhancement and source localization systems relies heavily on the simulation of room impulse response and multichannel diffuse noise, due to the lack of large-scale real-recorded datasets. However, the acoustic mismatch between simulated and real-world data could degrade the model performance when applying in real-world scenarios. To bridge this simulation-to-real gap, this paper presents a new relatively large-scale Real-recorded and annotated Microphone Array speech&Noise (RealMAN) dataset. The proposed dataset is valuable in two aspects: 1) benchmarking speech enhancement and localization algorithms in real scenarios; 2) offering a substantial amount of real-world training data for potentially improving the performance of real-world applications. Specifically, a 32-channel array with high-fidelity microphones is used for recording. A loudspeaker is used for playing source speech signals. A total of 83-hour speech signals (48 hours for static speaker and 35 hours for moving speaker) are recorded in 32 different scenes, and 144 hours of background noise are recorded in 31 different scenes. Both speech and noise recording scenes cover various common indoor, outdoor, semi-outdoor and transportation environments, which enables the training of general-purpose speech enhancement and source localization networks. To obtain the task-specific annotations, the azimuth angle of the loudspeaker is annotated with an omni-direction fisheye camera by automatically detecting the loudspeaker. The direct-path signal is set as the target clean speech for speech enhancement, which is obtained by filtering the source speech signal with an estimated direct-path propagation filter.

IPDnet: A Universal Direct-Path IPD Estimation Network for Sound Source Localization

Extracting direct-path spatial feature is crucial for sound source localization in adverse acoustic environments. This paper proposes the IPDnet, a neural network that estimates direct-path inter-channel phase difference (DP-IPD) of sound sources from microphone array signals. The estimated DP-IPD can be easily translated to source location based on the known microphone array geometry. First, a full-band and narrow-band fusion network is proposed for DP-IPD estimation, in which alternating narrow-band and full-band layers are responsible for estimating the rough DP-IPD information in one frequency band and capturing the frequency correlations of DP-IPD, respectively. Second, a new multi-track DP-IPD learning target is proposed for the localization of flexible number of sound sources. Third, the IPDnet is extend to handling variable microphone arrays, once trained which is able to process arbitrary microphone arrays with different number of channels and array topology. Experiments of multiple-moving-speaker localization are conducted on both simulated and real-world data, which show that the proposed full-band and narrow-band fusion network and the proposed multi-track DP-IPD learning target together achieves excellent sound source localization performance. Moreover, the proposed variable-array model generalizes well to unseen microphone arrays.

Self-Supervised Learning of Spatial Acoustic Representation with Cross-Channel Signal Reconstruction and Multi-Channel Conformer

Supervised learning methods have shown effectiveness in estimating spatial acoustic parameters such as time difference of arrival, direct-to-reverberant ratio and reverberation time. However, they still suffer from the simulation-to-reality generalization problem due to the mismatch between simulated and real-world acoustic characteristics and the deficiency of annotated real-world data. To this end, this work proposes a self-supervised method that takes full advantage of unlabeled data for spatial acoustic parameter estimation. First, a new pretext task, i.e. cross-channel signal reconstruction (CCSR), is designed to learn a universal spatial acoustic representation from unlabeled multi-channel microphone signals. We mask partial signals of one channel and ask the model to reconstruct them, which makes it possible to learn spatial acoustic information from unmasked signals and extract source information from the other microphone channel. An encoder-decoder structure is used to disentangle the two kinds of information. By fine-tuning the pre-trained spatial encoder with a small annotated dataset, this encoder can be used to estimate spatial acoustic parameters. Second, a novel multi-channel audio Conformer (MC-Conformer) is adopted as the encoder model architecture, which is suitable for both the pretext and downstream tasks. It is carefully designed to be able to capture the local and global characteristics of spatial acoustics exhibited in the time-frequency domain. Experimental results of five acoustic parameter estimation tasks on both simulated and real-world data show the effectiveness of the proposed method. To the best of our knowledge, this is the first self-supervised learning method in the field of spatial acoustic representation learning and multi-channel audio signal processing.

Aeroacoustic Source Localization

The deconvolutional DAMAS algorithm can effectively eliminate the misconceptions in the usually-used beamforming localization algorithm, allowing for more accurate calculation of the source location as well as the intensity. When solving a linear system of equations, the DAMAS algorithm takes into account the mutual influence of different locations, reducing or even eliminating sidelobes and producing more accurate results. This work first introduces the principles of the DAMAS algorithm. Then it applies both the beamforming algorithm and the DAMAS algorithm to simulate the localization of a single-frequency source from a 1.5 MW wind turbine, a complex line source with the text "UCAS" and a line source downstream of an airfoil trailing edge. Finally, the work presents experimental localization results of the source of a 1.5 MW wind turbine using both the beamforming algorithm and the DAMAS algorithm.

FN-SSL: Full-Band and Narrow-Band Fusion for Sound Source Localization

Extracting direct-path spatial features is critical for sound source localization in adverse acoustic environments. This paper proposes a full-band and narrow-band fusion network for estimating direct-path inter-channel phase difference (DP-IPD) from microphone signals. The alternating full-band and narrow-band layers are responsible for learning the full-band correlation and narrow-band extraction of DP-IPD, respectively. Experiments show that the proposed network noticeably outperforms other advanced methods on both simulated and real-world data.

Attention Mechanisms in Medical Image Segmentation: A Survey

Medical image segmentation plays an important role in computer-aided diagnosis. Attention mechanisms that distinguish important parts from irrelevant parts have been widely used in medical image segmentation tasks. This paper systematically reviews the basic principles of attention mechanisms and their applications in medical image segmentation. First, we review the basic concepts of attention mechanism and formulation. Second, we surveyed over 300 articles related to medical image segmentation, and divided them into two groups based on their attention mechanisms, non-Transformer attention and Transformer attention. In each group, we deeply analyze the attention mechanisms from three aspects based on the current literature work, i.e., the principle of the mechanism (what to use), implementation methods (how to use), and application tasks (where to use). We also thoroughly analyzed the advantages and limitations of their applications to different tasks. Finally, we summarize the current state of research and shortcomings in the field, and discuss the potential challenges in the future, including task specificity, robustness, standard evaluation, etc. We hope that this review can showcase the overall research context of traditional and Transformer attention methods, provide a clear reference for subsequent research, and inspire more advanced attention research, not only in medical image segmentation, but also in other image analysis scenarios.

xTrimoABFold: De novo Antibody Structure Prediction without MSA

In the field of antibody engineering, an essential task is to design a novel antibody whose paratopes bind to a specific antigen with correct epitopes. Understanding antibody structure and its paratope can facilitate a mechanistic understanding of its function. Therefore, antibody structure prediction from its sequence alone has always been a highly valuable problem for de novo antibody design. AlphaFold2, a breakthrough in the field of structural biology, provides a solution to predict protein structure based on protein sequences and computationally expensive coevolutionary multiple sequence alignments (MSAs). However, the computational efficiency and undesirable prediction accuracy of antibodies, especially on the complementarity-determining regions (CDRs) of antibodies limit their applications in the industrially high-throughput drug design. To learn an informative representation of antibodies, we employed a deep antibody language model (ALM) on curated sequences from the observed antibody space database via a transformer model. We also developed a novel model named xTrimoABFold to predict antibody structure from antibody sequence based on the pretrained ALM as well as efficient evoformers and structural modules. The model was trained end-to-end on the antibody structures in PDB by minimizing the ensemble loss of domain-specific focal loss on CDR and the frame-aligned point loss. xTrimoABFold outperforms AlphaFold2 and other protein language model based SOTAs, e.g., OmegaFold, HelixFold-Single, and IgFold with a large significant margin (30+\% improvement on RMSD) while performing 151 times faster than AlphaFold2. To the best of our knowledge, xTrimoABFold achieved state-of-the-art antibody structure prediction. Its improvement in both accuracy and efficiency makes it a valuable tool for de novo antibody design and could make further improvements in immuno-theory.

Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition

Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint dependencies and short-term trajectory but fails to directly model the distant joints relations and long-range temporal information that are vital to distinguishing various actions. To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal dimensions. Concretely, the MS-GC and MT-GC modules decompose the corresponding local graph convolution into a set of sub-graph convolution, forming a hierarchical residual architecture. Without introducing additional parameters, the features will be processed with a series of sub-graph convolutions, and each node could complete multiple spatial and temporal aggregations with its neighborhoods. The final equivalent receptive field is accordingly enlarged, which is capable of capturing both short- and long-range dependencies in spatial and temporal domains. By coupling these two modules as a basic block, we further propose a multi-scale spatial temporal graph convolutional network (MST-GCN), which stacks multiple blocks to learn effective motion representations for action recognition. The proposed MST-GCN achieves remarkable performance on three challenging benchmark datasets, NTU RGB+D, NTU-120 RGB+D and Kinetics-Skeleton, for skeleton-based action recognition.

AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation

Speaker adaptation in text-to-speech synthesis (TTS) is to finetune a pre-trained TTS model to adapt to new target speakers with limited data. While much effort has been conducted towards this task, seldom work has been performed for low computational resource scenarios due to the challenges raised by the requirement of the lightweight model and less computational complexity. In this paper, a tiny VITS-based TTS model, named AdaVITS, for low computing resource speaker adaptation is proposed. To effectively reduce parameters and computational complexity of VITS, an iSTFT-based wave construction decoder is proposed to replace the upsampling-based decoder which is resource-consuming in the original VITS. Besides, NanoFlow is introduced to share the density estimate across flow blocks to reduce the parameters of the prior encoder. Furthermore, to reduce the computational complexity of the textual encoder, scaled-dot attention is replaced with linear attention. To deal with the instability caused by the simplified model, instead of using the original text encoder, phonetic posteriorgram (PPG) is utilized as linguistic feature via a text-to-PPG module, which is then used as input for the encoder. Experiment shows that AdaVITS can generate stable and natural speech in speaker adaptation with 8.97M model parameters and 0.72GFlops computational complexity.