Related papers: E2E-MLT - an Unconstrained End-to-End Method for M…
Action recognition and localization in complex, untrimmed videos remain a formidable challenge in computer vision, largely due to the limitations of existing methods in capturing fine-grained actions, long-term temporal dependencies, and…
A novel interpretable end-to-end learning scheme for language identification is proposed. It is in line with the classical GMM i-vector methods both theoretically and practically. In the end-to-end pipeline, a general encoding layer is…
Scene-text image synthesis techniques that aim to naturally compose text instances on background scene images are very appealing for training deep neural networks due to their ability to provide accurate and comprehensive annotation…
Scene Text Recognition (STR) is the problem of recognizing the correct word or character sequence in a cropped word image. To obtain more robust output sequences, the notion of bidirectional STR has been introduced. So far, bidirectional…
The advent of large language models (LLMs) has predominantly catered to high-resource languages, leaving a disparity in performance for low-resource languages. Conventional Continual Training (CT) approaches to bridge this gap often…
Scene text recognition has recently been widely treated as a sequence-to-sequence prediction problem, where traditional fully-connected-LSTM (FC-LSTM) has played a critical role. Due to the limitation of FC-LSTM, existing methods have to…
This paper discusses the challenges of optical character recognition (OCR) on natural scenes, which is harder than OCR on documents due to the wild content and various image backgrounds. We propose to uniformly use word error rates (WER) as…
Multilingual automatic lyrics transcription (ALT) is a challenging task due to the limited availability of labelled data and the challenges introduced by singing, compared to multilingual automatic speech recognition. Although some…
Neural chat translation (NCT) aims to translate a cross-lingual chat between speakers of different languages. Existing context-aware NMT models cannot achieve satisfactory performances due to the following inherent problems: 1) limited…
In-Context Learning (ICL) has emerged as a new paradigm in large language models (LLMs), enabling them to perform novel tasks by conditioning on a few examples embedded in the prompt. Yet, the highly nonlinear behavior of ICL for NLP tasks…
Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with an incomplete source text, which is…
Mixture-of-Experts (MoE) models have emerged as a dominant paradigm for efficient LLM scaling, yet adapting them to non-English downstream tasks remains challenging. Existing fine-tuning approaches treat MoE models as monolithic learners,…
Streaming processing of speech audio is required for many contemporary practical speech recognition tasks. Even with the large corpora of manually transcribed speech data available today, it is impossible for such corpora to cover…
Machine Translation (MT) is a zone of concentrate in Natural Language processing which manages the programmed interpretation of human language, starting with one language then onto the next by the PC. Having a rich research history…
Recently, End-to-End (E2E) frameworks have achieved remarkable results on various Automatic Speech Recognition (ASR) tasks. However, Lattice-Free Maximum Mutual Information (LF-MMI), as one of the discriminative training criteria that show…
End-to-end (E2E) models in autonomous driving aim to directly map sensor inputs to control commands, but their ability to generalize to novel and complex scenarios remains a key challenge. The common practice of fully fine-tuning the vision…
Online construction of open-ended language scenes is crucial for robotic applications, where open-vocabulary interactive scene understanding is required. Recently, neural implicit representation has provided a promising direction for online…
Multilingual speech recognition for both monolingual and code-switching speech is a challenging task. Recently, based on the Mixture of Experts (MoE), many works have made good progress in multilingual and code-switching ASR, but present…
Recently, scene text detection has become an active research topic in computer vision and document analysis, because of its great importance and significant challenge. However, vast majority of the existing methods detect text within local…
End-to-end In-Image Machine Translation (IIMT) aims to convert text embedded within an image into a target language while preserving the original visual context, layout, and rendering style. However, existing IIMT benchmarks are largely…