Accurate recognition of specific categories, such as persons' names, dates or other identifiers is critical in many Automatic Speech Recognition (ASR) applications. As these categories represent personal information, ethical use of this data including collection, transcription, training and evaluation demands special care. One way of ensuring the security and privacy of individuals is to redact or eliminate Personally Identifiable Information (PII) from collection altogether. However, this results in ASR models that tend to have lower recognition accuracy of these categories. We use text-injection to improve the recognition of PII categories by including fake textual substitutes of PII categories in the training data using a text injection method. We demonstrate substantial improvement to Recall of Names and Dates in medical notes while improving overall WER. For alphanumeric digit sequences we show improvements to Character Error Rate and Sentence Accuracy.
Large language models have made significant strides in natural language processing, paving the way for innovative applications including molecular representation and generation. However, most existing single-modality approaches cannot capture the abundant and complex information in molecular data. Here, we introduce GIT-Mol, a multi-modal large language model that integrates the structure Graph, Image, and Text information, including the Simplified Molecular Input Line Entry System (SMILES) and molecular captions. To facilitate the integration of multi-modal molecular data, we propose GIT-Former, a novel architecture capable of mapping all modalities into a unified latent space. Our study develops an innovative any-to-language molecular translation strategy and achieves a 10%-15% improvement in molecular captioning, a 5%-10% accuracy increase in property prediction, and a 20% boost in molecule generation validity compared to baseline or single-modality models.
Convolutional Neural Networks (CNNs) have exhibited strong performance in medical image segmentation tasks by capturing high-level (local) information, such as edges and textures. However, due to the limited field of view of convolution kernel, it is hard for CNNs to fully represent global information. Recently, transformers have shown good performance for medical image segmentation due to their ability to better model long-range dependencies. Nevertheless, transformers struggle to capture high-level spatial features as effectively as CNNs. A good segmentation model should learn a better representation from local and global features to be both precise and semantically accurate. In our previous work, we proposed CATS, which is a U-shaped segmentation network augmented with transformer encoder. In this work, we further extend this model and propose CATS v2 with hybrid encoders. Specifically, hybrid encoders consist of a CNN-based encoder path paralleled to a transformer path with a shifted window, which better leverage both local and global information to produce robust 3D medical image segmentation. We fuse the information from the convolutional encoder and the transformer at the skip connections of different resolutions to form the final segmentation. The proposed method is evaluated on two public challenge datasets: Cross-Modality Domain Adaptation (CrossMoDA) and task 5 of Medical Segmentation Decathlon (MSD-5), to segment vestibular schwannoma (VS) and prostate, respectively. Compared with the state-of-the-art methods, our approach demonstrates superior performance in terms of higher Dice scores.
The generation of co-speech gestures for digital humans is an emerging area in the field of virtual human creation. Prior research has made progress by using acoustic and semantic information as input and adopting classify method to identify the person's ID and emotion for driving co-speech gesture generation. However, this endeavour still faces significant challenges. These challenges go beyond the intricate interplay between co-speech gestures, speech acoustic, and semantics; they also encompass the complexities associated with personality, emotion, and other obscure but important factors. This paper introduces "diffmotion-v2," a speech-conditional diffusion-based and non-autoregressive transformer-based generative model with WavLM pre-trained model. It can produce individual and stylized full-body co-speech gestures only using raw speech audio, eliminating the need for complex multimodal processing and manually annotated. Firstly, considering that speech audio not only contains acoustic and semantic features but also conveys personality traits, emotions, and more subtle information related to accompanying gestures, we pioneer the adaptation of WavLM, a large-scale pre-trained model, to extract low-level and high-level audio information. Secondly, we introduce an adaptive layer norm architecture in the transformer-based layer to learn the relationship between speech information and accompanying gestures. Extensive subjective evaluation experiments are conducted on the Trinity, ZEGGS, and BEAT datasets to confirm the WavLM and the model's ability to synthesize natural co-speech gestures with various styles.
Event forecasting has been a demanding and challenging task throughout the entire human history. It plays a pivotal role in crisis alarming and disaster prevention in various aspects of the whole society. The task of event forecasting aims to model the relational and temporal patterns based on historical events and makes forecasting to what will happen in the future. Most existing studies on event forecasting formulate it as a problem of link prediction on temporal event graphs. However, such pure structured formulation suffers from two main limitations: 1) most events fall into general and high-level types in the event ontology, and therefore they tend to be coarse-grained and offers little utility which inevitably harms the forecasting accuracy; and 2) the events defined by a fixed ontology are unable to retain the out-of-ontology contextual information. To address these limitations, we propose a novel task of context-aware event forecasting which incorporates auxiliary contextual information. First, the categorical context provides supplementary fine-grained information to the coarse-grained events. Second and more importantly, the context provides additional information towards specific situation and condition, which is crucial or even determinant to what will happen next. However, it is challenging to properly integrate context into the event forecasting framework, considering the complex patterns in the multi-context scenario. Towards this end, we design a novel framework named Separation and Collaboration Graph Disentanglement (short as SeCoGD) for context-aware event forecasting. Since there is no available dataset for this novel task, we construct three large-scale datasets based on GDELT. Experimental results demonstrate that our model outperforms a list of SOTA methods.
Machine learning provides many powerful and effective techniques for analysing heterogeneous electronic health records (EHR). Administrative Health Records (AHR) are a subset of EHR collected for administrative purposes, and the use of machine learning on AHRs is a growing subfield of EHR analytics. Existing reviews of EHR analytics emphasise that the data-modality of the EHR limits the breadth of suitable machine learning techniques, and pursuable healthcare applications. Despite emphasising the importance of data modality, the literature fails to analyse which techniques and applications are relevant to AHRs. AHRs contain uniquely well-structured, categorically encoded records which are distinct from other data-modalities captured by EHRs, and they can provide valuable information pertaining to how patients interact with the healthcare system. This paper systematically reviews AHR-based research, analysing 70 relevant studies and spanning multiple databases. We identify and analyse which machine learning techniques are applied to AHRs and which health informatics applications are pursued in AHR-based research. We also analyse how these techniques are applied in pursuit of each application, and identify the limitations of these approaches. We find that while AHR-based studies are disconnected from each other, the use of AHRs in health informatics research is substantial and accelerating. Our synthesis of these studies highlights the utility of AHRs for pursuing increasingly complex and diverse research objectives despite a number of pervading data- and technique-based limitations. Finally, through our findings, we propose a set of future research directions that can enhance the utility of AHR data and machine learning techniques for health informatics research.
Learned image compression methods have shown superior rate-distortion performance and remarkable potential compared to traditional compression methods. Most existing learned approaches use stacked convolution or window-based self-attention for transform coding, which aggregate spatial information in a fixed range. In this paper, we focus on extending spatial aggregation capability and propose a dynamic kernel-based transform coding. The proposed adaptive aggregation generates kernel offsets to capture valid information in the content-conditioned range to help transform. With the adaptive aggregation strategy and the sharing weights mechanism, our method can achieve promising transform capability with acceptable model complexity. Besides, according to the recent progress of entropy model, we define a generalized coarse-to-fine entropy model, considering the coarse global context, the channel-wise, and the spatial context. Based on it, we introduce dynamic kernel in hyper-prior to generate more expressive global context. Furthermore, we propose an asymmetric spatial-channel entropy model according to the investigation of the spatial characteristics of the grouped latents. The asymmetric entropy model aims to reduce statistical redundancy while maintaining coding efficiency. Experimental results demonstrate that our method achieves superior rate-distortion performance on three benchmarks compared to the state-of-the-art learning-based methods.
Contrastive graph node clustering via learnable data augmentation is a hot research spot in the field of unsupervised graph learning. The existing methods learn the sampling distribution of a pre-defined augmentation to generate data-driven augmentations automatically. Although promising clustering performance has been achieved, we observe that these strategies still rely on pre-defined augmentations, the semantics of the augmented graph can easily drift. The reliability of the augmented view semantics for contrastive learning can not be guaranteed, thus limiting the model performance. To address these problems, we propose a novel CONtrastiVe Graph ClustEring network with Reliable AugmenTation (COVERT). Specifically, in our method, the data augmentations are processed by the proposed reversible perturb-recover network. It distills reliable semantic information by recovering the perturbed latent embeddings. Moreover, to further guarantee the reliability of semantics, a novel semantic loss is presented to constrain the network via quantifying the perturbation and recovery. Lastly, a label-matching mechanism is designed to guide the model by clustering information through aligning the semantic labels and the selected high-confidence clustering pseudo labels. Extensive experimental results on seven datasets demonstrate the effectiveness of the proposed method. We release the code and appendix of CONVERT at https://github.com/xihongyang1999/CONVERT on GitHub.
Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications. The E2E ASR model implicitly learns an internal language model (LM) which characterises the training distribution of the source domain, and the E2E trainable nature makes the internal LM difficult to adapt to the target domain with text-only data To solve this problem, this paper proposes decoupled structures for attention-based encoder-decoder (Decoupled-AED) and neural transducer (Decoupled-Transducer) models, which can achieve flexible domain adaptation in both offline and online scenarios while maintaining robust intra-domain performance. To this end, the acoustic and linguistic parts of the E2E model decoder (or prediction network) are decoupled, making the linguistic component (i.e. internal LM) replaceable. When encountering a domain shift, the internal LM can be directly replaced during inference by a target-domain LM, without re-training or using domain-specific paired speech-text data. Experiments for E2E ASR models trained on the LibriSpeech-100h corpus showed that the proposed decoupled structure gave 15.1% and 17.2% relative word error rate reductions on the TED-LIUM 2 and AESRC2020 corpora while still maintaining performance on intra-domain data.
Quality-Diversity is a branch of stochastic optimization that is often applied to problems from the Reinforcement Learning and control domains in order to construct repertoires of well-performing policies/skills that exhibit diversity with respect to a behavior space. Such archives are usually composed of a finite number of reactive agents which are each associated to a unique behavior descriptor, and instantiating behavior descriptors outside of that coarsely discretized space is not straight-forward. While a few recent works suggest solutions to that issue, the trajectory that is generated is not easily customizable beyond the specification of a target behavior descriptor. We propose to jointly solve those problems in environments where semantic information about static scene elements is available by leveraging a Large Language Model to augment the repertoire with natural language descriptions of trajectories, and training a policy conditioned on those descriptions. Thus, our method allows a user to not only specify an arbitrary target behavior descriptor, but also provide the model with a high-level textual prompt to shape the generated trajectory. We also propose an LLM-based approach to evaluating the performance of such generative agents. Furthermore, we develop a benchmark based on simulated robot navigation in a 2d maze that we use for experimental validation.