United States

Recent Text-to-Speech (TTS) systems trained on reading or acted corpora have achieved near human-level naturalness. The diversity of human speech, however, often goes beyond the coverage of these corpora. We believe the ability to handle such diversity is crucial for AI systems to achieve human-level communication. Our work explores the use of more abundant real-world data for building speech synthesizers. We train TTS systems using real-world speech from YouTube and podcasts. We observe the mismatch between training and inference alignments in mel-spectrogram based autoregressive models, leading to unintelligible synthesis, and demonstrate that learned discrete codes within multiple code groups effectively resolves this issue. We introduce our MQTTS system whose architecture is designed for multiple code generation and monotonic alignment, along with the use of a clean silence prompt to improve synthesis quality. We conduct ablation analyses to identify the efficacy of our methods. We show that MQTTS outperforms existing TTS systems in several objective and subjective measures.

AAAI 2023

A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech

real-world speech synthesis

text-to-speech synthesis

snlp: generation

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

NAACL 2022

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

poster

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.

Vision Transformers (ViT) have made many breakthroughs in computer vision tasks. However, considerable redundancy arises in the spatial dimension of an input image, leading to massive computational costs. Therefore, We propose a coarse-to-fine vision transformer (CF-ViT) to relieve computational burden while retaining performance in this paper. Our proposed CF-ViT is motivated by two important observations in modern ViT models: (1) The coarse-grained patch splitting can locate informative regions of an input image. (2) Most images can be well recognized by a ViT model in a small-length token sequence.  Therefore, our CF-ViT implements network inference in a two-stage manner. At coarse inference stage, an input image is split into a small-length patch sequence for a computationally economical classification. If not well recognized, the informative patches are identified and further re-split in a fine-grained granularity.  Extensive experiments demonstrate the efficacy of our CF-ViT. For example, without any compromise on performance, CF-ViT reduces 53% FLOPs of LV-ViT, and also achieves 2.01x throughput.

CF-ViT: A General Coarse-to-Fine Method for Vision Transformer

Agents that plan and act in the real world must deal with the fact that time passes as they are planning. When timing is tight, there may be insufficient time to complete the search for a plan before it is time to act.  By commencing execution before search concludes, one gains time to search by making planning and execution concurrent. However, this incurs the risk of making incorrect action choices, especially if actions are irreversible. This tradeoff between opportunity and risk is the problem addressed in this paper. Our main contribution is to formally define this setting as an abstract metareasoning problem. We find that the abstract problem is intractable.  However, we identify special cases that are solvable in polynomial time, develop greedy solution algorithms, and, through tests on instances derived from search problems, find several methods that achieve promising practical performance.  This work lays the foundation for a principled time-aware executive that concurrently plans and executes.

A Formal Metareasoning Model of Concurrent Planning and Execution

Cooperative Multi-agent Reinforcement Learning (CMARL) has shown to be promising for many real-world applications. Previous works mainly focus on improving coordination ability via solving MARL-specific challenges (e.g., non-stationarity, credit assignment, scalability), but ignore the policy perturbation issue when testing in a different environment. This issue hasn't been considered in problem formulation or efficient algorithm design. To address this issue, we firstly model the problem as a Limited Policy Adversary Dec-POMDP (LPA-Dec-POMDP), where some coordinators from a team might accidentally and unpredictably encounter a limited number of malicious action attacks, but the regular coordinators still strive for the intended goal. Then, we propose \textbf{Ro}bust \textbf{M}ulti-\textbf{a}ge\textbf{n}t \textbf{C}oordination via \textbf{E}volutionary Generation of Auxiliary Adversarial Attackers (ROMANCE), which enables the trained policy to encounter diversified and strong auxiliary adversarial attacks during training, thus achieving high robustness under various 
policy perturbations. Concretely, to avoid the ego-system overfitting to a specific attacker, we maintain a set of attackers, which is optimized to guarantee the attackers high attacking quality and behavior diversity. The goal of quality is to minimize the ego-system coordination effect, and a novel diversity regularizer based on sparse action is applied to diversify the behaviors among attackers. The ego-system is then paired with a population of attackers selected from the maintained attacker set, and alternately trained against the constantly evolving attackers. Extensive experiments on multiple scenarios from SMAC indicate our ROMANCE provides comparable or better robustness and generalization ability than other baselines.

Robust Multi-agent Coordination via Evolutionary Generation of Auxiliary Adversarial Attackers

Robotic agents performing domestic chores by natural language directives are required to master the complex job of navigating environment and interacting with objects in the environments. The tasks given to the agents are often composite thus are challenging as completing them require to reason about multiple subtasks, e.g., bring a cup of coffee. To address the challenge, we propose to divide and conquer it by breaking the task into multiple subgoals and attend to them individually for better navigation and interaction. We call it Multi-level Compositional Reasoning Agent (MCR-Agent). Specifically, we learn a three-level action policy. At the highest level, we infer a sequence of human-interpretable subgoals to be executed based on language instructions by a high-level policy composition controller. At the middle level, we discriminatively control the agent’s navigation by a master policy by alternating between a navigation policy and various independent interaction policies. Finally, at the lowest level, we infer manipulation actions with the corresponding object masks using the appropriate interaction policy. Our approach not only generates human interpretable subgoals but also achieves 2.03% absolute gain to comparable state of the arts in the efficiency metric (PLWSR in unseen set) without using rule-based planning or a semantic spatial memory. The code is available at https://github.com/yonseivnl/mcr-agent.

Multi-level Compositional Reasoning for Interactive Instruction Following

Gradient inversion attacks on federated learning systems reconstruct client training data from exchanged gradient information. To defend against such attacks, a variety of defense mechanisms were proposed. However, they usually lead to an unacceptable trade-off between privacy and model utility. Recent observations suggest that dropout could mitigate gradient leakage and improve model utility if added to neural networks. Unfortunately, this phenomenon has not been systematically researched yet. In this work, we thoroughly analyze the effect of dropout on iterative gradient inversion attacks. We find that state of the art attacks are not able to reconstruct the client data due to the stochasticity induced by dropout during model training. Nonetheless, we argue that dropout does not offer reliable protection if the dropout induced stochasticity is adequately modeled during attack optimization. Consequently, we propose a novel Dropout Inversion Attack (DIA) that jointly optimizes for client data and dropout masks to approximate the stochastic client model. We conduct an extensive systematic evaluation of our attack on four seminal model architectures and three image classification datasets of increasing complexity. We find that our proposed attack bypasses the protection seemingly induced by dropout and reconstructs client data with high fidelity. Our work demonstrates that privacy inducing changes to model architectures alone cannot be assumed to reliably protect from gradient leakage and therefore should be combined with complementary defense mechanisms.

Dropout is NOT All You Need to Prevent Gradient Leakage

Although the distortion correction of fisheye images has been extensively studied, the correction of fisheye videos is still an elusive challenge. For different frames of the fisheye video, the existing image correction methods ignore the correlation of sequences, resulting in temporal jitter in the corrected video. To solve this problem, we propose a temporal weighting scheme to get a plausible global optical flow, which mitigates the jitter effect by progressively reducing the weight of frames. Subsequently, we observe that the inter-frame optical flow of the video is facilitated to perceive the local spatial deformation of the fisheye video. Therefore, we derive the spatial deformation through the flows of fisheye and distorted-free videos, thereby enhancing the local accuracy of the predicted result. However, the independent correction for each frame disrupts the temporal correlation. Due to the property of fisheye video, a distorted moving object may be able to find its distorted-free pattern at another moment. To this end, a temporal deformation aggregator is designed to reconstruct the deformation correlation between frames and provide a reliable global feature. Our method achieves an end-to-end correction and demonstrates superiority in correction quality and stability compared with the SOTA correction methods.

Spatiotemporal Deformation Perception for Fisheye Video Rectification

Sorted L-One Penalized Estimation (SLOPE) has shown the nice theoretical property as well as empirical behavior recently on the false discovery rate (FDR) control of high-dimensional feature selection by adaptively imposing the non-increasing sequence of tuning parameters on the sorted L1 penalties. This paper goes beyond the previous concern limited to the FDR control by considering the stepdown-based SLOPE in order to control the probability of k or more false rejections (k-FWER) and the false discovery proportion (FDP). Two new SLOPEs, called k-SLOPE and F-SLOPE, are proposed to realize k-FWER and FDP control respectively, where the stepdown procedure is injected into the SLOPE scheme. For the proposed stepdown SLOPEs, we establish their theoretical guarantees on controlling k-FWER and FDP under the orthogonal design setting, and also provide an intuitive guideline for the choice of regularization parameter sequence in much general setting. Empirical evaluations on simulated data validate the effectiveness of our approaches on controlled feature selection and support our theoretical findings.

Stepdown SLOPE for Controlled Feature Selection

As we all know, multi-view data is more expressive than single-view data and multi-label annotation enjoys richer supervision information than single-label, which makes multi-view multi-label learning widely applicable for various pattern recognition tasks. In this complex representation learning problem, three main challenges can be characterized as follows: i) How to learn consistent representations of samples across all views? ii) How to exploit and utilize category correlations of multi-label to guide inference? iii) How to avoid the negative impact resulting from the incompleteness of views or labels? To cope with these problems, we propose a general multi-view multi-label learning framework named label-guided masked view- and category-aware transformers in this paper. First, we design two transformer-style based modules for cross-view features aggregation and multi-label classification, respectively. The former aggregates information from different views in the process of extracting view-specific features, and the latter learns subcategory embedding to improve classification performance. Second, considering the imbalance of expressive power among views, an adaptively weighted view fusion module is proposed to obtain view-consistent embedding features. Third, we impose a label manifold constraint in sample-level representation learning to maximize the utilization of supervised information. Last but not least, all the modules are designed under the premise of incomplete views and labels, which makes our method adaptable to arbitrary multi-view and multi-label data. Extensive experiments on five datasets confirm that our method has clear advantages over other state-of-the-art methods.

Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers

Transformer-based text-to-image synthesis generates images from abstractive textual conditions and achieves prompt results. Since transformer-based models predict visual tokens step by step in testing, where the early error is hard to be corrected and would be propagated. To alleviate this issue, the common practice is drawing multi-paths from the transformer-based models and re-ranking the multi-images decoded from multi-paths to find the best one and filter out others. Therefore, the computing procedure of excluding images may be inefficient. To improve the effectiveness and efficiency of decoding, we exploit a reject decoding algorithm with tiny multi-modal models to enlarge the searching space and exclude the useless paths as early as possible. Specifically, we build tiny multi-modal models to evaluate the similarities between the partial paths and the caption at multi scales. Then, we propose a reject decoding algorithm to exclude some lowest quality partial paths at the inner steps. Thus, under the same computing load as the original decoding, we could search across more multi-paths to improve the decoding efficiency and synthesizing quality. The experiments conducted on the MS-COCO dataset and large-scale datasets show that the proposed reject decoding algorithm can exclude the useless paths and enlarge the searching paths to improve the synthesizing quality by consuming less time.

Reject Decoding via Language-Vision Models for Text-to-Image Synthesis

We propose a novel algorithm for generalized linear contextual bandits (GLBs) with an $\tilde{O}(\sqrt{\kappa^{-1} \phi^{-1} T})$ regret over $T$ rounds where $\phi$ is the minimum eigenvalue of the covariance of contexts and $\kappa$ is a lower bound of the variance of rewards. 
In several identified cases of $\phi^{-1}=O(d)$, where $d$ is the dimension of contexts, our result is the first regret bound for generalized linear  bandits (GLBs) achieving the order $\sqrt{d}$ without discarding the observed rewards.
Previous approaches achieve the regret bound of order $\sqrt{d}$ by discarding the observed rewards, whereas our algorithm achieves the bound incorporating contexts from all arms in our double doubly-robust (DDR) estimator.
The DDR estimator is a subclass of doubly-robust estimator but with a tighter error bound.
We also provide an $O(\kappa^{-1} \phi^{-1} \log (NT) \log T)$ regret bound for $N$ arms under a probabilistic margin condition.
This is the first regret bound under the margin condition for linear models or GLMs when contexts are different for all arms but coefficients are common.
We conduct empirical studies using synthetic data and real examples, demonstrating the effectiveness of our algorithm.

Downloads

Next from AAAI 2023

CF-ViT: A General Coarse-to-Fine Method for Vision Transformer

Similar lecture

Towards Unsupervised Speech Synthesis