Audio-visual speech enhancement (AV-SE) aims to enhance degraded speech along with extra visual information such as lip videos, and has been shown to be more effective than audio-only speech enhancement. This paper proposes the incorporation of ultrasound tongue images to improve the performance of lip-based AV-SE systems further. To address the challenge of acquiring ultrasound tongue images during inference, we first propose to employ knowledge distillation during training to investigate the feasibility of leveraging tongue-related information without directly inputting ultrasound tongue images. Specifically, we guide an audio-lip speech enhancement student model to learn from a pre-trained audio-lip-tongue speech enhancement teacher model, thus transferring tongue-related knowledge. To better model the alignment between the lip and tongue modalities, we further propose the introduction of a lip-tongue key-value memory network into the AV-SE model. This network enables the retrieval of tongue features based on readily available lip features, thereby assisting the subsequent speech enhancement task. Experimental results demonstrate that both methods significantly improve the quality and intelligibility of the enhanced speech compared to traditional lip-based AV-SE baselines. Moreover, both proposed methods exhibit strong generalization performance on unseen speakers and in the presence of unseen noises. Furthermore, phone error rate (PER) analysis of automatic speech recognition (ASR) reveals that while all phonemes benefit from introducing ultrasound tongue images, palatal and velar consonants benefit most.
相關內容
Recent advancements in pre-trained large-scale language-image models have ushered in a new era of visual comprehension, offering a significant leap forward. These breakthroughs have proven particularly instrumental in addressing long-standing challenges that were previously daunting. Leveraging these innovative techniques, this paper tackles two well-known issues within the realm of visual analytics: (1) the efficient exploration of large-scale image datasets and identification of potential data biases within them; (2) the evaluation of image captions and steering of their generation process. On the one hand, by visually examining the captions automatically generated from language-image models for an image dataset, we gain deeper insights into the semantic underpinnings of the visual contents, unearthing data biases that may be entrenched within the dataset. On the other hand, by depicting the association between visual contents and textual captions, we expose the weaknesses of pre-trained language-image models in their captioning capability and propose an interactive interface to steer caption generation. The two parts have been coalesced into a coordinated visual analytics system, fostering mutual enrichment of visual and textual elements. We validate the effectiveness of the system with domain practitioners through concrete case studies with large-scale image datasets.
We demonstrate text as a strong cross-modal interface. Rather than relying on deep embeddings to connect image and language as the interface representation, our approach represents an image as text, from which we enjoy the interpretability and flexibility inherent to natural language. We employ an autoencoder that uses a pre-trained text-to-image diffusion model for decoding. The encoder is trained to transform an input image into text, which is then fed into the fixed text-to-image diffusion decoder to reconstruct the original input -- a process we term De-Diffusion. Experiments validate both the precision and comprehensiveness of De-Diffusion text representing images, such that it can be readily ingested by off-the-shelf text-to-image tools and LLMs for diverse multi-modal tasks. For example, a single De-Diffusion model can generalize to provide transferable prompts for different text-to-image tools, and also achieves a new state of the art on open-ended vision-language tasks by simply prompting large language models with few-shot examples.
Pixel-based language models process text rendered as images, which allows them to handle any script, making them a promising approach to open vocabulary language modelling. However, recent approaches use text renderers that produce a large set of almost-equivalent input patches, which may prove sub-optimal for downstream tasks, due to redundancy in the input representations. In this paper, we investigate four approaches to rendering text in the PIXEL model (Rust et al., 2023), and find that simple character bigram rendering brings improved performance on sentence-level tasks without compromising performance on token-level or multilingual tasks. This new rendering strategy also makes it possible to train a more compact model with only 22M parameters that performs on par with the original 86M parameter model. Our analyses show that character bigram rendering leads to a consistently better model but with an anisotropic patch embedding space, driven by a patch frequency bias, highlighting the connections between image patch- and tokenization-based language models.
Visual-Semantic Embedding (VSE) networks can help search engines better understand the meaning behind visual content and associate it with relevant textual information, leading to more accurate search results. VSE networks can be used in cross-modal search engines to embed image and textual descriptions in a shared space, enabling image-to-text and text-to-image retrieval tasks. However, the full potential of VSE networks for search engines has yet to be fully explored. This paper presents Boon, a novel cross-modal search engine that combines two state-of-the-art networks: the GPT-3.5-turbo large language model, and the VSE network VITR (VIsion Transformers with Relation-focused learning) to enhance the engine's capabilities in extracting and reasoning with regional relationships in images. VITR employs encoders from CLIP that were trained with 400 million image-description pairs and it was fine-turned on the RefCOCOg dataset. Boon's neural-based components serve as its main functionalities: 1) a 'cross-modal search engine' that enables end-users to perform image-to-text and text-to-image retrieval. 2) a 'multi-lingual conversational AI' component that enables the end-user to converse about one or more images selected by the end-user. Such a feature makes the search engine accessible to a wide audience, including those with visual impairments. 3) Boon is multi-lingual and can take queries and handle conversations about images in multiple languages. Boon was implemented using the Django and PyTorch frameworks. The interface and capabilities of the Boon search engine are demonstrated using the RefCOCOg dataset, and the engine's ability to search for multimedia through the web is facilitated by Google's API.
Existing multimodal machine translation (MMT) datasets consist of images and video captions or instructional video subtitles, which rarely contain linguistic ambiguity, making visual information ineffective in generating appropriate translations. Recent work has constructed an ambiguous subtitles dataset to alleviate this problem but is still limited to the problem that videos do not necessarily contribute to disambiguation. We introduce EVA (Extensive training set and Video-helpful evaluation set for Ambiguous subtitles translation), an MMT dataset containing 852k Japanese-English (Ja-En) parallel subtitle pairs, 520k Chinese-English (Zh-En) parallel subtitle pairs, and corresponding video clips collected from movies and TV episodes. In addition to the extensive training set, EVA contains a video-helpful evaluation set in which subtitles are ambiguous, and videos are guaranteed helpful for disambiguation. Furthermore, we propose SAFA, an MMT model based on the Selective Attention model with two novel methods: Frame attention loss and Ambiguity augmentation, aiming to use videos in EVA for disambiguation fully. Experiments on EVA show that visual information and the proposed methods can boost translation performance, and our model performs significantly better than existing MMT models. The EVA dataset and the SAFA model are available at: //github.com/ku-nlp/video-helpful-MMT.git.
Convolutional neural networks (CNNs) have shown dramatic improvements in single image super-resolution (SISR) by using large-scale external samples. Despite their remarkable performance based on the external dataset, they cannot exploit internal information within a specific image. Another problem is that they are applicable only to the specific condition of data that they are supervised. For instance, the low-resolution (LR) image should be a "bicubic" downsampled noise-free image from a high-resolution (HR) one. To address both issues, zero-shot super-resolution (ZSSR) has been proposed for flexible internal learning. However, they require thousands of gradient updates, i.e., long inference time. In this paper, we present Meta-Transfer Learning for Zero-Shot Super-Resolution (MZSR), which leverages ZSSR. Precisely, it is based on finding a generic initial parameter that is suitable for internal learning. Thus, we can exploit both external and internal information, where one single gradient update can yield quite considerable results. (See Figure 1). With our method, the network can quickly adapt to a given image condition. In this respect, our method can be applied to a large spectrum of image conditions within a fast adaptation process.
We present a new method to learn video representations from large-scale unlabeled video data. Ideally, this representation will be generic and transferable, directly usable for new tasks such as action recognition and zero or few-shot learning. We formulate unsupervised representation learning as a multi-modal, multi-task learning problem, where the representations are shared across different modalities via distillation. Further, we introduce the concept of loss function evolution by using an evolutionary search algorithm to automatically find optimal combination of loss functions capturing many (self-supervised) tasks and modalities. Thirdly, we propose an unsupervised representation evaluation metric using distribution matching to a large unlabeled dataset as a prior constraint, based on Zipf's law. This unsupervised constraint, which is not guided by any labeling, produces similar results to weakly-supervised, task-specific ones. The proposed unsupervised representation learning results in a single RGB network and outperforms previous methods. Notably, it is also more effective than several label-based methods (e.g., ImageNet), with the exception of large, fully labeled video datasets.
Learning with limited data is a key challenge for visual recognition. Few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them is the target task. In this paper, we propose a novel approach to adapt the embedding model to the target classification task, yielding embeddings that are task-specific and are discriminative. To this end, we employ a type of self-attention mechanism called Transformer to transform the embeddings from task-agnostic to task-specific by focusing on relating instances from the test instances to the training instances in both seen and unseen classes. Our approach also extends to both transductive and generalized few-shot classification, two important settings that have essential use cases. We verify the effectiveness of our model on two standard benchmark few-shot classification datasets --- MiniImageNet and CUB, where our approach demonstrates state-of-the-art empirical performance.
Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for many applications: 1) the lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this work, we present an approach based on disentangled representation for producing diverse outputs without paired training images. To achieve diversity, we propose to embed images onto two spaces: a domain-invariant content space capturing shared information across domains and a domain-specific attribute space. Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time. To handle unpaired training data, we introduce a novel cross-cycle consistency loss based on disentangled representations. Qualitative results show that our model can generate diverse and realistic images on a wide range of tasks without paired training data. For quantitative comparisons, we measure realism with user study and diversity with a perceptual distance metric. We apply the proposed model to domain adaptation and show competitive performance when compared to the state-of-the-art on the MNIST-M and the LineMod datasets.
Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work, we propose a combined bottom-up and top-down attention mechanism that enables attention to be calculated at the level of objects and other salient image regions. This is the natural basis for attention to be considered. Within our approach, the bottom-up mechanism (based on Faster R-CNN) proposes image regions, each with an associated feature vector, while the top-down mechanism determines feature weightings. Applying this approach to image captioning, our results on the MSCOCO test server establish a new state-of-the-art for the task, achieving CIDEr / SPICE / BLEU-4 scores of 117.9, 21.5 and 36.9, respectively. Demonstrating the broad applicability of the method, applying the same approach to VQA we obtain first place in the 2017 VQA Challenge.
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