United States

Face-based speech synthesis provides a practical solution to generate voices from human faces. However, directly using 2D face images leads to the problems of uninterpretability and entanglement. In this paper, to address the issues, we introduce 3D face shape which (1) has an anatomical relationship between voice characteristics, partaking in the ``bone conduction&quot; of human timbre production, and (2) is naturally independent of irrelevant factors by excluding the blending process. 
We devise a three-stage framework to generate speech from 3D face shapes. Fully considering timbre production in anatomical and acquired terms, our framework incorporates three additional relevant attributes including face texture, facial features, and demographics. Experiments and subjective tests demonstrate our method can generate utterances matching faces well, with good audio quality and voice diversity. We also explore and visualize how the voice changes with the face. Case studies show that our method upgrades the face-voice inference to personalized custom-made voice creating, revealing a promising prospect in virtual human and dubbing applications.

AAAI 2023

What Does Your Face Sound Like? 3D Face Shape Towards Voice

voice characteristics

face-voice correlation

speech synthesis

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

Face-based speech synthesis provides a practical solution to generate voices from human faces. However, directly using 2D face images leads to the problems of uninterpretability and entanglement. In this paper, to address the issues, we introduce 3D face shape which (1) has an anatomical relationship between voice characteristics, partaking in the ``bone conduction" of human timbre production, and (2) is naturally independent of irrelevant factors by excluding the blending process. 
We devise a three-stage framework to generate speech from 3D face shapes. Fully considering timbre production in anatomical and acquired terms, our framework incorporates three additional relevant attributes including face texture, facial features, and demographics. Experiments and subjective tests demonstrate our method can generate utterances matching faces well, with good audio quality and voice diversity. We also explore and visualize how the voice changes with the face. Case studies show that our method upgrades the face-voice inference to personalized custom-made voice creating, revealing a promising prospect in virtual human and dubbing applications.

poster

Multivariate time series forecasting with hierarchical structure
is widely used in real-world applications, e.g., sales
predictions for the geographical hierarchy formed by cities,
states, and countries. The hierarchical time series (HTS) forecasting
includes two sub-tasks, i.e., forecasting and reconciliation.
In the previous works, hierarchical information is only
integrated in the reconciliation step to maintain coherency,
but not in forecasting step for accuracy improvement. In this
paper, we propose two novel tree-based feature integration
mechanisms, i.e., top-down convolution and bottom-up attention
to leverage the information of the hierarchical structure
to improve the forecasting performance. Moreover, unlike
most previous reconciliation methods which either rely
on strong assumptions or focus on coherent constraints only,
we utilize deep neural optimization networks, which not only
achieve coherency without any assumptions, but also allow
more flexible and realistic constraints to achieve task-based
targets, e.g., lower under-estimation penalty and meaningful
decision-making loss to facilitate the subsequent downstream
tasks. Experiments on real-world datasets demonstrate that
our tree-based feature integration mechanism achieves superior
performances on hierarchical forecasting tasks compared
to the state-of-the-art methods, and our neural optimization
networks can be applied to real-world tasks effectively without
any additional effort under coherence and task-based constraints.

SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchies

Semantic scene completion (SSC) aims to complete a partial 3D scene and predict its semantics simultaneously. Most existing works adopt the voxel representations, thus suffering from the growth of memory and computation cost as the voxel resolution increases. Though a few works attempt to solve SSC from the perspective of 3D point clouds, they have not fully exploited the correlation and complementarity between the two tasks of scene completion and semantic segmentation. In our work, we present CasFusionNet, a novel cascaded network for point cloud semantic scene completion by dense feature fusion. Specifically, we design (i) a global completion module (GCM) to produce an upsampled and completed but coarse point set, (ii) a semantic segmentation module (SSM) to predict the per-point semantic labels of the completed points generated by GCM, and (iii) a local refinement module (LRM) to further refine the coarse completed points and the associated labels from a local perspective. We organize the above three modules via dense feature fusion in each level, and cascade a total of four levels, where we also employ feature fusion between each level for sufficient information usage. Both quantitative and qualitative results on our compiled two point-based datasets validate the effectiveness and superiority of our CasFusionNet compared to state-of-the-art methods in terms of both scene completion and semantic segmentation. The codes and datasets are available at: https://github.com/JinfengX/CasFusionNet.

CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion

Conventional graph neural networks (GNNs) are often confronted with fairness issues that may stem from their input, including node attributes and neighbors surrounding a node. While several recent approaches have been proposed to eliminate the bias rooted in sensitive attributes, they ignore the other key input of GNNs, namely the neighbors of a node, which can introduce bias since GNNs hinge on neighborhood structures to generate node representations. In particular, the varying neighborhood structures across nodes, manifesting themselves in drastically different node degrees, give rise to the diverse behaviors of nodes and biased outcomes. In this paper, we first define and generalize the degree bias using a generalized definition of node degree as a manifestation and quantification of different multi-hop structures around different nodes. To address the bias in the context of node classification, we propose a novel GNN framework called Generalized Degree Fairness-centric Graph Neural Network (DegFairGNN). Specifically, in each GNN layer, we employ a learnable debiasing function to generate debiasing contexts, which modulate the layer-wise neighborhood aggregation to eliminate the degree bias originating from the diverse degrees among nodes. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our model on both accuracy and fairness metrics.

On Generalized Degree Fairness in Graph Neural Networks

The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting. However, task confusion is not well assessed within this framework, e.g., the discrepancy between classes of different tasks is not well learned (i.e., inter-task confusion, ITC), and certain priority is still given to the latest class batch (i.e., old-new confusion, ONC). We empirically validate the side effects of the two types of confusion. Meanwhile, a novel solution called Task Correlated Incremental Learning (TCIL) is proposed to encourage discriminative and fair feature utilization across tasks. TCIL performs a multi-level knowledge distillation to propagate knowledge learned from old tasks to the new one. It establishes information flow paths at both feature and logit levels, enabling the learning to be aware of old classes. Besides, attention mechanism and classifier re-scoring are applied to generate more fair classification scores. We conduct extensive experiments on CIFAR100 and ImageNet100 datasets. The results demonstrate that TCIL consistently achieves state-of-the-art accuracy. It mitigates both ITC and ONC, while showing advantages in battle with catastrophic forgetting even no rehearsal memory is reserved.

Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning

Event-based cameras are bio-inspired sensors that capture brightness change of every pixel in an asynchronous manner. Compared with frame-based sensors, event cameras have microsecond-level latency and high dynamic range, hence showing great potential for object detection under high-speed motion and poor illumination conditions. Due to sparsity and asynchronism nature with event streams, most of existing approaches resort to hand-crafted methods to convert event data into 2D grid representation. However, they are sub-optimal in aggregating information from event stream for object detection. In this work, we propose to learn an event representation optimized for event-based object detection. Specifically, event streams are divided into grids in the x-y-t coordinates for both positive and negative polarity, producing a set of pillars as 3D tensor representation. To fully exploit information with event streams to detect objects, a dual-memory aggregation network (DMANet) is proposed to leverage both long and short memory along event streams to aggregate effective information for object detection. Long memory is encoded in the hidden state of adaptive convLSTMs while short memory is modeled by computing spatial-temporal correlation between event pillars at neighboring time intervals. Extensive experiments on the recently released event-based automotive detection dataset demonstrate the effectiveness of the proposed method.

Dual Memory Aggregation Network for Event-based Object Detection with Learnable Representation

Federated learning has attracted increasing attention with the emergence of distributed data. While extensive federated learning algorithms have been proposed for the non-convex distributed problem, the federated learning in practice still faces numerous challenges, such as the large training iterations to converge since the sizes of models and datasets keep increasing, and the lack of adaptivity by SGD-based model updates. Meanwhile, the study of adaptive methods in federated learning is scarce and existing works either lack a complete theoretical convergence guarantee or have slow sample complexity. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on the momentum-based variance reduced technique in cross-silo FL. We first explore how to design the adaptive algorithm in the FL setting. By providing a counter-example, we prove that a simple combination of FL and adaptive methods could lead to divergence. More importantly, we provide a convergence analysis for our method and prove that our algorithm is the first adaptive FL algorithm to reach the best-known samples $O(\epsilon^{-3})$ and $O(\epsilon^{-2})$ communication rounds to find an $\epsilon$-stationary point without large batches. The experimental results on the language modeling task and image classification task with heterogeneous data demonstrate the efficiency of our algorithms.

Faster Adaptive Federated Learning

Vision Transformers (ViTs) have a radically different architecture with significantly less inductive bias than Convolutional Neural Networks. Along with the improvement in performance, security and robustness of ViTs are also of great importance to study. In contrast to many recent works that exploit the robustness of ViTs against adversarial examples, this paper investigates a representative causative attack, i.e., backdoor. We first examine the vulnerability of ViTs against various backdoor attacks and find that ViTs are also quite vulnerable to existing  attacks. However, we observe that the clean-data accuracy and backdoor attack success rate of ViTs respond distinctively to patch transformations before the positional encoding. Then, based on this finding, we propose an effective method for ViTs to defend both patch-based and blending-based trigger backdoor attacks via patch processing.
The performances are evaluated on several benchmark datasets, including CIFAR10, GTSRB, and TinyImageNet, which show the proposedds defense is very successful in mitigating backdoor attacks for ViTs. To the best of our knowledge, this paper presents the first defensive strategy that utilizes a unique characteristic of ViTs against backdoor attacks.

Defending Backdoor Attacks on Vision Transformer via Patch Processing

Recently, researchers have applied the word-character lattice framework to integrated word information, which has become very popular for Chinese named entity recognition (NER).  However, prior approaches fuse word information by different variants of encoders such as Lattice LSTM or Flat-Lattice Transformer, but are still not data-efficient indeed to fully grasp the depth interaction of cross-granularity and important word information from the lexicon. In this paper, we go
beyond the typical lattice structure and propose a novel Multi-Granularity Contrastive Learning (MGCL) framework, that aims to optimize the inter-granularity distribution distance and emphasize the critical matched words in the lexicon.  By
carefully combining cross-granularity contrastive learning and bi-granularity contrastive learning, the network can explicitly leverage lexicon information at the data level based on the lattice structure, and further provide better representations of across-granularity, thus significantly improving model performance. Experiments on four Chinese NER datasets show that MGCL obtains state-of-the-art results while considering model efficiency.

MCL: Multi-Granularity Contrastive Learning Framework for Chinese NER

Applications abound in which optimization problems must be repeatedly solved, each time with new (but similar) data. Analytic optimization algorithms can be hand-designed to provably solve these problems in an iterative fashion. On one hand, data-driven algorithms can "learn to optimize" (L2O)  with much fewer iterations and   similar cost per iteration as general-purpose optimization algorithms. On the other hand, unfortunately, many L2O algorithms lack converge guarantees. To fuse the advantages of these approaches, we present a Safe-L2O framework. Safe-L2O updates incorporate a safeguard to guarantee convergence for convex problems with proximal and/or gradient oracles. The safeguard is simple and computationally cheap to implement, and it is activated only when the data-driven L2O updates would perform poorly or appear to diverge. This yields the numerical benefits of employing machine learning   to create rapid L2O algorithms while still guaranteeing convergence. Our numerical examples show convergence of Safe-L2O algorithms, even when the provided data is not from the distribution of training data.

Safeguarded Learned Convex Optimization

Heterogeneous graph neural networks (HGNs) are prominent approaches to node classification tasks on heterogeneous graphs. Despite the superior performance, insights about the predictions made from HGNs are obscure to humans. Existing explainability techniques are mainly proposed for GNNs on homogeneous graphs. They focus on highlighting salient graph objects to the predictions whereas the problem of how these objects affect the predictions remains unsolved. Given heterogeneous graphs with complex structures and rich semantics, it is imperative that salient objects can be accompanied with their influence paths to the predictions, unveiling the reasoning process of HGNs. In this paper, we develop xPath, a new framework that provides fine-grained explanations for black-box HGNs specifying a cause node with its influence path to the target node. In xPath, we differentiate the influence of a node on the prediction w.r.t. every individual influence path, and measure the influence by perturbing graph structure via a novel graph rewiring algorithm. Furthermore, we introduce a greedy search algorithm to find the most influential fine-grained explanations efficiently. Empirical results on various HGNs and heterogeneous graphs show that xPath yields faithful explanations efficiently, outperforming the adaptations of advanced GNN explanation approaches.

Downloads

Next from AAAI 2023

SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchies

Similar lecture

Zero-shot Face-based Voice Conversion: Bottleneck-Free Speech Disentanglement in the Real-world Scenario