Fine-Grained Grounding for Multimodal Speech Recognition
This work addresses the challenge of enhancing speech recognition accuracy for multimodal systems by localizing relevant visual cues, though it is incremental as it builds on existing methods with a focus on specific data.
The paper tackles the problem of improving multimodal speech recognition by using finer-grained visual information from specific image regions instead of global features, resulting in better recovery of a broader range of word types like adjectives and verbs on the Flickr8K Audio Captions Corpus.
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 model's ability to localize the correct proposals.