اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدFine-Grained Grounding for Multimodal Speech Recognition
84
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Multimodal automatic speech recognition systems integrate information from images to improve speech recognition quality, by grounding the speech in the visual context. While visual signals have been shown to be useful for recovering entities that have been masked in the audio, these models should be capable of recovering a broader range of word types. Existing systems rely on global visual features that represent the entire image, but localizing the relevant regions of the image will make it possible to recover a larger set of words, such as adjectives and verbs. In this paper, we propose a model that uses finer-grained visual information from different parts of the image, using automatic object proposals. In experiments on the Flickr8K Audio Captions Corpus, we find that our model improves over approaches that use global visual features, that the proposals enable the model to recover entities and other related words, such as adjectives, and that improvements are due to the models ability to localize the correct proposals.
قيم البحث
اقرأ أيضاً
Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or to recall
named entities. Motivated by this, there have been many works studying the integration of visual information into the speech recognition pipeline. Specifically, in our previous work, we propose a multistep visual adaptive training approach which improves the accuracy of an audio-based Automatic Speech Recognition (ASR) system. This approach, however, is not end-to-end as it requires fine-tuning the whole model with an adaptation layer. In this paper, we propose novel end-to-end multimodal ASR systems and compare them to the adaptive approach by using a range of visual representations obtained from state-of-the-art convolutional neural networks. We show that adaptive training is effective for S2S models leading to an absolute improvement of 1.4% in word error rate. As for the end-to-end systems, although they perform better than baseline, the improvements are slightly less than adaptive training, 0.8 absolute WER reduction in single-best models. Using ensemble decoding, end-to-end models reach a WER of 15% which is the lowest score among all systems.
Automated knowledge discovery from trending chemical literature is essential for more efficient biomedical research. How to extract detailed knowledge about chemical reactions from the core chemistry literature is a new emerging challenge that has no
t been well studied. In this paper, we study the new problem of fine-grained chemical entity typing, which poses interesting new challenges especially because of the complex name mentions frequently occurring in chemistry literature and graphic representation of entities. We introduce a new benchmark data set (CHEMET) to facilitate the study of the new task and propose a novel multi-modal representation learning framework to solve the problem of fine-grained chemical entity typing by leveraging external resources with chemical structures and using cross-modal attention to learn effective representation of text in the chemistry domain. Experiment results show that the proposed framework outperforms multiple state-of-the-art methods.
Visual context has been shown to be useful for automatic speech recognition (ASR) systems when the speech signal is noisy or corrupted. Previous work, however, has only demonstrated the utility of visual context in an unrealistic setting, where a fix
ed set of words are systematically masked in the audio. In this paper, we simulate a more realistic masking scenario during model training, called RandWordMask, where the masking can occur for any word segment. Our experiments on the Flickr 8K Audio Captions Corpus show that multimodal ASR can generalize to recover different types of masked words in this unstructured masking setting. Moreover, our analysis shows that our models are capable of attending to the visual signal when the audio signal is corrupted. These results show that multimodal ASR systems can leverage the visual signal in more generalized noisy scenarios.
In this paper, we introduce the NameRec* task, which aims to do highly accurate and fine-grained person name recognition. Traditional Named Entity Recognition models have good performance in recognising well-formed person names from text with consist
ent and complete syntax, such as news articles. However, there are rapidly growing scenarios where sentences are of incomplete syntax and names are in various forms such as user-generated contents and academic homepages. To address person name recognition in this context, we propose a fine-grained annotation scheme based on anthroponymy. To take full advantage of the fine-grained annotations, we propose a Co-guided Neural Network (CogNN) for person name recognition. CogNN fully explores the intra-sentence context and rich training signals of name forms. To better utilize the inter-sentence context and implicit relations, which are extremely essential for recognizing person names in long documents, we further propose an Inter-sentence BERT Model (IsBERT). IsBERT has an overlapped input processor, and an inter-sentence encoder with bidirectional overlapped contextual embedding learning and multi-hop inference mechanisms. To derive benefit from different documents with a diverse abundance of context, we propose an advanced Adaptive Inter-sentence BERT Model (Ada-IsBERT) to dynamically adjust the inter-sentence overlapping ratio to different documents. We conduct extensive experiments to demonstrate the superiority of the proposed methods on both academic homepages and news articles.
In the following paper, we present and discuss challenging applications for fine-grained visual classification (FGVC): biodiversity and species analysis. We not only give details about two challenging new datasets suitable for computer vision researc
h with up to 675 highly similar classes, but also present first results with localized features using convolutional neural networks (CNN). We conclude with a list of challenging new research directions in the area of visual classification for biodiversity research.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
