Related papers: Improving Stability in Simultaneous Speech Transla…

Code-switching (CS) automatic speech recognition (ASR) faces challenges due to the language confusion resulting from accents, auditory similarity, and seamless language switches. Adaptation on the pre-trained multi-lingual model has shown…

The scattering of light impacts sensing and communication technologies throughout the electromagnetic spectrum. Overcoming the effects of time-varying scattering media is particularly challenging. In this article we introduce a new way to…

Neural machine translation (NMT) is notoriously sensitive to noises, but noises are almost inevitable in practice. One special kind of noise is the homophone noise, where words are replaced by other words with similar pronunciations. We…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

As large-scale language model pretraining pushes the state-of-the-art in text generation, recent work has turned to controlling attributes of the text such models generate. While modifying the pretrained models via fine-tuning remains the…

Image translation for change detection or classification in bi-temporal remote sensing images is unique. Although it can acquire paired images, it is still unsupervised. Moreover, strict semantic preservation in translation is always needed…

Text generation is of great importance to many natural language processing applications. However, maximization-based decoding methods (e.g. beam search) of neural language models often lead to degenerate solutions -- the generated text is…

Modern Machine Translation (MT) systems perform consistently well on clean, in-domain text. However most human generated text, particularly in the realm of social media, is full of typos, slang, dialect, idiolect and other noise which can…

Bi-directional LSTMs are a powerful tool for text representation. On the other hand, they have been shown to suffer various limitations due to their sequential nature. We investigate an alternative LSTM structure for encoding text, which…

This paper proposes a decoding strategy for end-to-end simultaneous speech translation. We leverage end-to-end models trained in offline mode and conduct an empirical study for two language pairs (English-to-German and…

With the extensive use of vision-language models in various downstream tasks, evaluating their robustness is crucial. In this paper, we propose a benchmark for assessing the robustness of vision-language models. We believe that a robust…

With the growing influence of Large Language Models (LLMs), there is increasing interest in integrating speech representations with them to enable more seamless multi-modal processing and speech understanding. This study introduces a novel…

Recently abstractive spoken language summarization raises emerging research interest, and neural sequence-to-sequence approaches have brought significant performance improvement. However, summarizing long meeting transcripts remains…

Text-to-image models, such as Stable Diffusion (SD), undergo iterative updates to improve image quality and address concerns such as safety. Improvements in image quality are straightforward to assess. However, how model updates resolve…

In recent years, automatic speech-to-speech and speech-to-text translation has gained momentum thanks to advances in artificial intelligence, especially in the domains of speech recognition and machine translation. The quality of such…

Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and environments. In this paper, we report…

The method of wavefront shaping to control optical properties of opaque media is a promising technique for authentication applications. One of the main challenges of this technique is the sensitivity of the wavefront-sample coupling to…

The presence of specific linguistic signals particular to a certain sub-group can become highly salient to language models during training. In automated decision-making settings, this may lead to biased outcomes when models rely on cues…

Recent text-to-image diffusion models have significantly improved visual quality and text alignment. However, generating a sequence of images while preserving consistent character identity across diverse scene descriptions remains a…

Scene text recognition has received increased attention in the research community. Text in the wild often possesses irregular arrangements, typically including perspective text, curved text, oriented text. Most existing methods are hard to…