Affect is an emotional characteristic encompassing valence, arousal, and intensity, and is a crucial attribute for enabling authentic conversations. While existing text-to-speech (TTS) and speech-to-speech systems rely on strength embedding vectors and global style tokens to capture emotions, these models represent emotions as a component of style or represent them in discrete categories. We propose AffectEcho, an emotion translation model, that uses a Vector Quantized codebook to model emotions within a quantized space featuring five levels of affect intensity to capture complex nuances and subtle differences in the same emotion. The quantized emotional embeddings are implicitly derived from spoken speech samples, eliminating the need for one-hot vectors or explicit strength embeddings. Experimental results demonstrate the effectiveness of our approach in controlling the emotions of generated speech while preserving identity, style, and emotional cadence unique to each speaker. We showcase the language-independent emotion modeling capability of the quantized emotional embeddings learned from a bilingual (English and Chinese) speech corpus with an emotion transfer task from a reference speech to a target speech. We achieve state-of-art results on both qualitative and quantitative metrics.
相關內容
語音合成（Speech Synthesis），也稱為文語轉換（Text-to-Speech, TTS,它是將任意的輸入文本轉換成自然流暢的語音輸出。語音合成涉及到人工智能、心理學、聲學、語言學、數字信號處理、計算機科學等多個學科技術，是信息處理領域中的一項前沿技術。
隨著計算機技術的不斷提高，語音合成技術從早期的共振峰合成,逐步發展為波形拼接合成和統計參數語音合成，再發展到混合語音合成；合成語音的質量、自然度已經得到明顯提高，基本能滿足一些特定場合的應用需求。目前，語音合成技術在銀行、醫院等的信息播報系統、汽車導航系統、自動應答呼叫中心等都有廣泛應用，取得了巨大的經濟效益。
另外，隨著智能手機、MP3、PDA 等與我們生活密切相關的媒介的大量涌現，語音合成的應用也在逐漸向娛樂、語音教學、康復治療等領域深入。可以說語音合成正在影響著人們生活的方方面面。
Anomaly detection (AD) in surface inspection is an essential yet challenging task in manufacturing due to the quantity imbalance problem of scarce abnormal data. To overcome the above, a reconstruction encoder-decoder (ED) such as autoencoder or U-Net which is trained with only anomaly-free samples is widely adopted, in the hope that unseen abnormals should yield a larger reconstruction error than normal. Over the past years, researches on self-supervised reconstruction-by-inpainting have been reported. They mask out suspected defective regions for inpainting in order to make them invisible to the reconstruction ED to deliberately cause inaccurate reconstruction for abnormals. However, their limitation is multiple random masking to cover the whole input image due to defective regions not being known in advance. We propose a novel reconstruction-by-inpainting method dubbed Excision and Recovery (EAR) that features single deterministic masking. For this, we exploit a pre-trained spatial attention model to predict potential suspected defective regions that should be masked out. We also employ a variant of U-Net as our ED to further limit the reconstruction ability of the U-Net model for abnormals, in which skip connections of different layers can be selectively disabled. In the training phase, all the skip connections are switched on to fully take the benefits from the U-Net architecture. In contrast, for inferencing, we only keep deeper skip connections with shallower connections off. We validate the effectiveness of EAR using an MNIST pre-trained attention for a commonly used surface AD dataset, KolektorSDD2. The experimental results show that EAR achieves both better AD performance and higher throughput than state-of-the-art methods. We expect that the proposed EAR model can be widely adopted as training and inference strategies for AD purposes.
Large Language Models (LLMs) have the ability to solve a variety of tasks, such as text summarization and mathematical questions, just out of the box, but they are often trained with a single task in mind. Due to high computational costs, the current trend is to use prompt instruction tuning to better adjust monolithic, pretrained LLMs for new -- but often individual -- downstream tasks. Thus, how one would expand prompt tuning to handle -- concomitantly -- heterogeneous tasks and data distributions is a widely open question. To address this gap, we suggest the use of \emph{Mixture of Prompts}, or MoPs, associated with smart gating functionality: the latter -- whose design is one of the contributions of this paper -- can identify relevant skills embedded in different groups of prompts and dynamically assign combined experts (i.e., collection of prompts), based on the target task. Additionally, MoPs are empirically agnostic to any model compression technique applied -- for efficiency reasons -- as well as instruction data source and task composition. In practice, MoPs can simultaneously mitigate prompt training "interference" in multi-task, multi-source scenarios (e.g., task and data heterogeneity across sources), as well as possible implications from model approximations. As a highlight, MoPs manage to decrease final perplexity from $\sim20\%$ up to $\sim70\%$, as compared to baselines, in the federated scenario, and from $\sim 3\%$ up to $\sim30\%$ in the centralized scenario.
3D printers enable end-users to design and fabricate unique physical artifacts but maintain an increased entry barrier and friction. End users must design tangible artifacts through intangible media away from the main problem space (ex-situ) and transfer spatial requirements to an abstract software environment. To allow users to evaluate dimensions, balance, or fit early and in-situ, we developed BrickStARt, a design tool using tangible construction blocks paired with a mixed-reality headset. Users assemble a physical block model at the envisioned location of the fabricated artifact. Designs can be tested tangibly, refined, and digitally post-processed, remaining continuously in-situ. We implemented BrickStARt using a Magic Leap headset and present walkthroughs, highlighting novel interactions for 3D design. In a user study (n=16), first-time 3D modelers succeeded more often using BrickStARt than Tinkercad. Our results suggest that BrickStARt provides an accessible and explorative process while facilitating quick, tangible design iterations that allow users to detect physics-related issues (e.g., clearance) early on.
There is a niche of companies responsible for intermediating the purchase of large batches of varied products for other companies, for which the main challenge is to perform product description standardization, i.e., matching an item described by a client with a product described in a catalog. The problem is complex since the client's product description may be: (1) potentially noisy; (2) short and uninformative (e.g., missing information about model and size); and (3) cross-language. In this paper, we formalize this problem as a ranking task: given an initial client product specification (query), return the most appropriate standardized descriptions (response). In this paper, we propose TPDR, a two-step Transformer-based Product and Class Description Retrieval method that is able to explore the semantic correspondence between IS and SD, by exploiting attention mechanisms and contrastive learning. First, TPDR employs the transformers as two encoders sharing the embedding vector space: one for encoding the IS and another for the SD, in which corresponding pairs (IS, SD) must be close in the vector space. Closeness is further enforced by a contrastive learning mechanism leveraging a specialized loss function. TPDR also exploits a (second) re-ranking step based on syntactic features that are very important for the exact matching (model, dimension) of certain products that may have been neglected by the transformers. To evaluate our proposal, we consider 11 datasets from a real company, covering different application contexts. Our solution was able to retrieve the correct standardized product before the 5th ranking position in 71% of the cases and its correct category in the first position in 80% of the situations. Moreover, the effectiveness gains over purely syntactic or semantic baselines reach up to 3.7 times, solving cases that none of the approaches in isolation can do by themselves.
Temporal motif mining is the task of finding the occurrences of subgraph patterns within a large input temporal graph that obey the specified structural and temporal constraints. Despite its utility in several critical application domains that demand high performance (e.g., detecting fraud in financial transaction graphs), the performance of existing software is limited on commercial hardware platforms, in that it runs for tens of hours. This paper presents Everest - a system that efficiently maps the workload of mining (supports both enumeration and counting) temporal motifs to the highly parallel GPU architecture. In particular, using an input temporal graph and a more expressive user-defined temporal motif query definition compared to prior works, Everest generates an execution plan and runtime primitives that optimize the workload execution by exploiting the high compute throughput of a GPU. Everest generates motif-specific mining code to reduce long-latency memory accesses and frequent thread divergence operations. Everest incorporates novel low-cost runtime mechanisms to enable load balancing to improve GPU hardware utilization. To support large graphs that do not fit on GPU memory, Everest also supports multi-GPU execution by intelligently partitioning the edge list that prevents inter-GPU communication. Everest hides the implementation complexity of presented optimizations away from the targeted system user for better usability. Our evaluation shows that, using proposed optimizations, Everest improves the performance of a baseline GPU implementation by 19x, on average.
The existence of representative datasets is a prerequisite of many successful artificial intelligence and machine learning models. However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training. The reasons for this are manifold and range from time and cost constraints to ethical considerations. As a consequence, the reliable use of these models, especially in safety-critical applications, is a huge challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches, and eventually to increase the generalization capability of these models. Furthermore, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-based models with existing knowledge. The identified approaches are structured according to the categories integration, extraction and conformity. Special attention is given to applications in the field of autonomous driving.
Generative commonsense reasoning which aims to empower machines to generate sentences with the capacity of reasoning over a set of concepts is a critical bottleneck for text generation. Even the state-of-the-art pre-trained language generation models struggle at this task and often produce implausible and anomalous sentences. One reason is that they rarely consider incorporating the knowledge graph which can provide rich relational information among the commonsense concepts. To promote the ability of commonsense reasoning for text generation, we propose a novel knowledge graph augmented pre-trained language generation model KG-BART, which encompasses the complex relations of concepts through the knowledge graph and produces more logical and natural sentences as output. Moreover, KG-BART can leverage the graph attention to aggregate the rich concept semantics that enhances the model generalization on unseen concept sets. Experiments on benchmark CommonGen dataset verify the effectiveness of our proposed approach by comparing with several strong pre-trained language generation models, particularly KG-BART outperforms BART by 5.80, 4.60, in terms of BLEU-3, 4. Moreover, we also show that the generated context by our model can work as background scenarios to benefit downstream commonsense QA tasks.
Named entity recognition (NER) is the task to identify text spans that mention named entities, and to classify them into predefined categories such as person, location, organization etc. NER serves as the basis for a variety of natural language applications such as question answering, text summarization, and machine translation. Although early NER systems are successful in producing decent recognition accuracy, they often require much human effort in carefully designing rules or features. In recent years, deep learning, empowered by continuous real-valued vector representations and semantic composition through nonlinear processing, has been employed in NER systems, yielding stat-of-the-art performance. In this paper, we provide a comprehensive review on existing deep learning techniques for NER. We first introduce NER resources, including tagged NER corpora and off-the-shelf NER tools. Then, we systematically categorize existing works based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder. Next, we survey the most representative methods for recent applied techniques of deep learning in new NER problem settings and applications. Finally, we present readers with the challenges faced by NER systems and outline future directions in this area.
We introduce a multi-task setup of identifying and classifying entities, relations, and coreference clusters in scientific articles. We create SciERC, a dataset that includes annotations for all three tasks and develop a unified framework called Scientific Information Extractor (SciIE) for with shared span representations. The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links. Experiments show that our multi-task model outperforms previous models in scientific information extraction without using any domain-specific features. We further show that the framework supports construction of a scientific knowledge graph, which we use to analyze information in scientific literature.
Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even more importance compared with the answer itself, since it makes the question and answering process more understandable and traceable. To this end, we propose a new task of VQA-E (VQA with Explanation), where the computational models are required to generate an explanation with the predicted answer. We first construct a new dataset, and then frame the VQA-E problem in a multi-task learning architecture. Our VQA-E dataset is automatically derived from the VQA v2 dataset by intelligently exploiting the available captions. We have conducted a user study to validate the quality of explanations synthesized by our method. We quantitatively show that the additional supervision from explanations can not only produce insightful textual sentences to justify the answers, but also improve the performance of answer prediction. Our model outperforms the state-of-the-art methods by a clear margin on the VQA v2 dataset.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191