Simultaneous sequence generation is a pivotal task for real-time scenarios, such as streaming speech recognition, simultaneous machine translation and simultaneous speech translation, where the target sequence is generated while receiving the source sequence. The crux of achieving high-quality generation with low latency lies in identifying the optimal moments for generating, accomplished by learning a mapping between the source and target sequences. However, existing methods often rely on task-specific heuristics for different sequence types, limiting the model's capacity to adaptively learn the source-target mapping and hindering the exploration of multi-task learning for various simultaneous tasks. In this paper, we propose a unified segment-to-segment framework (Seg2Seg) for simultaneous sequence generation, which learns the mapping in an adaptive and unified manner. During the process of simultaneous generation, the model alternates between waiting for a source segment and generating a target segment, making the segment serve as the natural bridge between the source and target. To accomplish this, Seg2Seg introduces a latent segment as the pivot between source to target and explores all potential source-target mappings via the proposed expectation training, thereby learning the optimal moments for generating. Experiments on multiple simultaneous generation tasks demonstrate that Seg2Seg achieves state-of-the-art performance and exhibits better generality across various tasks.
相關內容
We devise a version of Linear Temporal Logic (LTL) on a denotational domain of streams. We investigate this logic in terms of domain theory, (point-free) topology and geometric logic. This yields the first steps toward an extension of the "Domain Theory in Logical Form" paradigm to temporal liveness properties. We show that the negation-free formulae of LTL induce sober subspaces of streams, but that this is in general not the case in presence of negation. We propose a direct, inductive, translation of negation-free LTL to geometric logic. This translation reflects the approximations used to compute the usual fixpoint representations of LTL modalities. As a motivating example, we handle a natural input-output specification for the usual filter function on streams.
Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep dive into their temporal motions and interactions. Inherently, object pairs and their relationships enjoy spatial co-occurrence correlations within each image and temporal consistency/transition correlations across different images, which can serve as prior knowledge to facilitate VidSGG model learning and inference. In this work, we propose a spatial-temporal knowledge-embedded transformer (STKET) that incorporates the prior spatial-temporal knowledge into the multi-head cross-attention mechanism to learn more representative relationship representations. Specifically, we first learn spatial co-occurrence and temporal transition correlations in a statistical manner. Then, we design spatial and temporal knowledge-embedded layers that introduce the multi-head cross-attention mechanism to fully explore the interaction between visual representation and the knowledge to generate spatial- and temporal-embedded representations, respectively. Finally, we aggregate these representations for each subject-object pair to predict the final semantic labels and their relationships. Extensive experiments show that STKET outperforms current competing algorithms by a large margin, e.g., improving the mR@50 by 8.1%, 4.7%, and 2.1% on different settings over current algorithms.
In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It is possible to achieve human-like recognition without the need to build a pronunciation dictionary in advance. However, due to the relative scarcity of training data on code-switching, the performance of ASR models tends to degrade drastically when encountering this phenomenon. Most past studies have simplified the learning complexity of the model by splitting the code-switching task into multiple tasks dealing with a single language and then learning the domain-specific knowledge of each language separately. Therefore, in this paper, we attempt to introduce language identification information into the middle layer of the ASR model's encoder. We aim to generate acoustic features that imply language distinctions in a more implicit way, reducing the model's confusion when dealing with language switching.
The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, which is essential in multilingual speech recognition. Recent studies have attempted to address this setting by separating the modules for different languages to ensure distinct latent representations for languages. Some other methods considered the switching mechanism based on language identification. In this study, a new attention-guided adaptation is proposed to conduct parameter-efficient learning for bilingual ASR. This method selects those attention heads in a model which closely express language identities and then guided those heads to be correctly attended with their corresponding languages. The experiments on the Mandarin-English code-switching speech corpus show that the proposed approach achieves a 14.2% mixed error rate, surpassing state-of-the-art method, where only 5.6% additional parameters over Whisper are trained.
Recently audio-visual speech recognition (AVSR), which better leverages video modality as additional information to extend automatic speech recognition (ASR), has shown promising results in complex acoustic environments. However, there is still substantial space to improve as complex computation of visual modules and ineffective fusion of audio-visual modalities. To eliminate these drawbacks, we propose a down-up sampling-based AVSR model (Hourglass-AVSR) to enjoy high efficiency and performance, whose time length is scaled during the intermediate processing, resembling an hourglass. Firstly, we propose a context and residual aware video upsampling approach to improve the recognition performance, which utilizes contextual information from visual representations and captures residual information between adjacent video frames. Secondly, we introduce a visual-audio alignment approach during the upsampling by explicitly incorporating boundary constraint loss. Besides, we propose a cross-layer attention fusion to capture the modality dependencies within each visual encoder layer. Experiments conducted on the MISP-AVSR dataset reveal that our proposed Hourglass-AVSR model outperforms ASR model by 12.9% and 20.8% relative concatenated minimum permutation character error rate (cpCER) reduction on far-field and middle-field test sets, respectively. Moreover, compared to other state-of-the-art AVSR models, our model exhibits the highest improvement in cpCER for the visual module. Furthermore, on the benefit of our down-up sampling approach, Hourglass-AVSR model reduces 54.2% overall computation costs with minor performance degradation.
The integration of advanced video codecs into the streaming pipeline is growing in response to the increasing demand for high quality video content. However, the significant computational demand for advanced codecs like Versatile Video Coding (VVC) poses challenges for service providers, including longer encoding time and higher encoding cost. This challenge becomes even more pronounced in streaming, as the same content needs to be encoded at multiple bitrates (also known as representations) to accommodate different network conditions. To accelerate the encoding process of multiple representations of the same content in VVC, we employ the encoding map of a single representation, known as the reference representation, and utilize its partitioning structure to accelerate the encoding of the remaining representations, referred to as dependent representations. To ensure compatibility with parallel processing, we designate the lowest bitrate representation as the reference representation. The experimental results indicate a substantial improvement in the encoding time for the dependent representations, achieving an average reduction of 40%, while maintaining a minimal average quality drop of only 0.43 in Video Multi-method Assessment Fusion (VMAF). This improvement is observed when utilizing Versatile Video Encoder (VVenC), an open and optimized VVC encoder implementation.
Optimizing static risk-averse objectives in Markov decision processes is difficult because they do not admit standard dynamic programming equations common in Reinforcement Learning (RL) algorithms. Dynamic programming decompositions that augment the state space with discrete risk levels have recently gained popularity in the RL community. Prior work has shown that these decompositions are optimal when the risk level is discretized sufficiently. However, we show that these popular decompositions for Conditional-Value-at-Risk (CVaR) and Entropic-Value-at-Risk (EVaR) are inherently suboptimal regardless of the discretization level. In particular, we show that a saddle point property assumed to hold in prior literature may be violated. However, a decomposition does hold for Value-at-Risk and our proof demonstrates how this risk measure differs from CVaR and EVaR. Our findings are significant because risk-averse algorithms are used in high-stake environments, making their correctness much more critical.
Unlike opaque object, novel view synthesis of transparent object is a challenging task, because transparent object refracts light of background causing visual distortions on the transparent object surface along the viewpoint change. Recently introduced Neural Radiance Fields (NeRF) is a view synthesis method. Thanks to its remarkable performance improvement, lots of following applications based on NeRF in various topics have been developed. However, if an object with a different refractive index is included in a scene such as transparent object, NeRF shows limited performance because refracted light ray at the surface of the transparent object is not appropriately considered. To resolve the problem, we propose a NeRF-based method consisting of the following three steps: First, we reconstruct a three-dimensional shape of a transparent object using visual hull. Second, we simulate the refraction of the rays inside of the transparent object according to Snell's law. Last, we sample points through refracted rays and put them into NeRF. Experimental evaluation results demonstrate that our method addresses the limitation of conventional NeRF with transparent objects.
Intraoperative ultrasound imaging is used to facilitate safe brain tumour resection. However, due to challenges with image interpretation and the physical scanning, this tool has yet to achieve widespread adoption in neurosurgery. In this paper, we introduce the components and workflow of a novel, versatile robotic platform for intraoperative ultrasound tissue scanning in neurosurgery. An RGB-D camera attached to the robotic arm allows for automatic object localisation with ArUco markers, and 3D surface reconstruction as a triangular mesh using the ImFusion Suite software solution. Impedance controlled guidance of the US probe along arbitrary surfaces, represented as a mesh, enables collaborative US scanning, i.e., autonomous, teleoperated and hands-on guided data acquisition. A preliminary experiment evaluates the suitability of the conceptual workflow and system components for probe landing on a custom-made soft-tissue phantom. Further assessment in future experiments will be necessary to prove the effectiveness of the presented platform.
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable Reasoning Network that employs an interpretable, hop-by-hop reasoning process for question answering. The model dynamically decides which part of an input question should be analyzed at each hop; predicts a relation that corresponds to the current parsed results; utilizes the predicted relation to update the question representation and the state of the reasoning process; and then drives the next-hop reasoning. Experiments show that our model yields state-of-the-art results on two datasets. More interestingly, the model can offer traceable and observable intermediate predictions for reasoning analysis and failure diagnosis, thereby allowing manual manipulation in predicting the final answer.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191