Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is complicated and time-consuming, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs in training and use predicted values in inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of fully end-to-end inference. Experimental results show that 1) FastSpeech 2 achieves a 3x training speed-up over FastSpeech, and FastSpeech 2s enjoys even faster inference speed; 2) FastSpeech 2 and 2s outperform FastSpeech in voice quality, and FastSpeech 2 can even surpass autoregressive models. Audio samples are available at https://speechresearch.github.io/fastspeech2/.

Manually constructing a Wordnet is a difficult task, needing years of experts' time. As a first step to automatically construct full Wordnets, we propose approaches to generate Wordnet synsets for languages both resource-rich and resource-poor, using publicly available Wordnets, a machine translator and/or a single bilingual dictionary. Our algorithms translate synsets of existing Wordnets to a target language T, then apply a ranking method on the translation candidates to find best translations in T. Our approaches are applicable to any language which has at least one existing bilingual dictionary translating from English to it.

Across infrastructure domains, physical damage caused by storms and other weather events often requires costly and time-sensitive repairs to restore services as quickly as possible. While recent studies have used agent-based models to estimate the cost of repairs, the implemented strategies for assignment of repair crews to different locations are generally human-driven or based on simple rules. In order to find performant strategies, we continue with an agent-based model, but approach this problem as a combinational optimization problem known as the Minimum Weighted Latency Problem for multiple repair crews. We apply a partitioning algorithm that balances the assignment of targets amongst all the crews using two different heuristics that optimize either the importance of repair locations or the travel time between them. We benchmark our algorithm on both randomly generated graphs as well as data derived from a real-world urban environment, and show that our algorithm delivers significantly better assignments than existing methods.

This paper examines approaches to generate lexical resources for endangered languages. Our algorithms construct bilingual dictionaries and multilingual thesauruses using public Wordnets and a machine translator (MT). Since our work relies on only one bilingual dictionary between an endangered language and an "intermediate helper" language, it is applicable to languages that lack many existing resources.

The humble video game movie tends to get it from all sides. Critics turn up their noses and gaming nerds are often equally hard to please, albeit on very different points of principle. Kids are perhaps the most forgiving demographic for the video game film, which is why the belated Sonic the Hedgehog film franchise has done well to squarely target them. It gets the job done, perhaps a little too thoroughly at more than two hours in length. Many of the best video game adaptations succeed by making it all a bit of a joke.

Tag-aware recommendation is a task of predicting a personalized list of items for a user by their tagging behaviors. It is crucial for many applications with tagging capabilities like last.fm or movielens. Recently, many efforts have been devoted to improving Tag-aware recommendation systems (TRS) with Graph Convolutional Networks (GCN), which has become new state-of-the-art for the general recommendation. However, some solutions are directly inherited from GCN without justifications, which is difficult to alleviate the sparsity, ambiguity, and redundancy issues introduced by tags, thus adding to difficulties of training and degrading recommendation performance. In this work, we aim to simplify the design of GCN to make it more concise for TRS. We propose a novel tag-aware recommendation model named Light Folksonomy Graph Collaborative Filtering (LFGCF), which only includes the essential GCN components. Specifically, LFGCF first constructs Folksonomy Graphs from the records of user assigning tags and item getting tagged. Then we leverage the simple design of aggregation to learn the high-order representations on Folksonomy Graphs and use the weighted sum of the embeddings learned at several layers for information updating. We share tags embeddings to bridge the information gap between users and items. Besides, a regularization function named TransRT is proposed to better depict user preferences and item features. Extensive hyperparameters experiments and ablation studies on three real-world datasets show that LFGCF uses fewer parameters and significantly outperforms most baselines for the tag-aware top-N recommendations.

Fatal diseases, as Critical Health Episodes (CHEs), represent real dangers for patients hospitalized in Intensive Care Units. These episodes can lead to irreversible organ damage and death. Nevertheless, diagnosing them in time would greatly reduce their inconvenience. This study therefore focused on building a highly effective early warning system for CHEs such as Acute Hypotensive Episodes and Tachycardia Episodes. To facilitate the precocity of the prediction, a gap of one hour was considered between the observation periods (Observation Windows) and the periods during which a critical event can occur (Target Windows). The MIMIC II dataset was used to evaluate the performance of the proposed system. This system first includes extracting additional features using three different modes. Then, the feature selection process allowing the selection of the most relevant features was performed using the Mutual Information Gain feature importance. Finally, the high-performance predictive model LightGBM was used to perform episode classification. This approach called MIG-LightGBM was evaluated using five different metrics: Event Recall (ER), Reduced Precision (RP), average Anticipation Time (aveAT), average False Alarms (aveFA), and Event F1-score (EF1-score). A method is therefore considered highly efficient for the early prediction of CHEs if it exhibits not only a large aveAT but also a large EF1-score and a low aveFA. Compared to systems using Extreme Gradient Boosting, Support Vector Classification or Naive Bayes as a predictive model, the proposed system was found to be highly dominant. It also confirmed its superiority over the Layered Learning approach.

The importance of building text-to-SQL parsers which can be applied to new databases has long been acknowledged, and a critical step to achieve this goal is schema linking, i.e., properly recognizing mentions of unseen columns or tables when generating SQLs. In this work, we propose a novel framework to elicit relational structures from large-scale pre-trained language models (PLMs) via a probing procedure based on Poincar\'e distance metric, and use the induced relations to augment current graph-based parsers for better schema linking. Compared with commonly-used rule-based methods for schema linking, we found that probing relations can robustly capture semantic correspondences, even when surface forms of mentions and entities differ. Moreover, our probing procedure is entirely unsupervised and requires no additional parameters. Extensive experiments show that our framework sets new state-of-the-art performance on three benchmarks. We empirically verify that our probing procedure can indeed find desired relational structures through qualitative analysis. Our code can be found at https://github.com/AlibabaResearch/DAMO-ConvAI.

There is strong interest in the generation of synthetic video imagery of people talking for various purposes, including entertainment, communication, training, and advertisement. With the development of deep fake generation models, synthetic video imagery will soon be visually indistinguishable to the naked eye from a naturally capture video. In addition, many methods are continuing to improve to avoid more careful, forensic visual analysis. Some deep fake videos are produced through the use of facial puppetry, which directly controls the head and face of the synthetic image through the movements of the actor, allow the actor to 'puppet' the image of another. In this paper, we address the question of whether one person's movements can be distinguished from the original speaker by controlling the visual appearance of the speaker but transferring the behavior signals from another source. We conduct a study by comparing synthetic imagery that: 1) originates from a different person speaking a different utterance, 2) originates from the same person speaking a different utterance, and 3) originates from a different person speaking the same utterance. Our study shows that synthetic videos in all three cases are seen as less real and less engaging than the original source video. Our results indicate that there could be a behavioral signature that is detectable from a person's movements that is separate from their visual appearance, and that this behavioral signature could be used to distinguish a deep fake from a properly captured video.

Releasing a new artificial intelligence system that learns from people on the internet can be a risky proposition. Just ask Microsoft's "teen" chatbot Tay--except you can't, because Tay was taken down when it started reproducing sexist and racist remarks shortly after it launched in 2016. Meta apparently believes that AI can learn to do better. The company just announced BlenderBot 3, a much more advanced chatbot designed to learn through conversation without getting into the kind of trouble that derailed Tay. And the company has made it available for anyone to try out.