相关论文: REINA: Regularized Entropy Information-Based Loss …

End-to-end Speech Translation (ST) models have several advantages such as lower latency, smaller model size, and less error compounding over conventional pipelines that combine Automatic Speech Recognition (ASR) and text Machine Translation…

Transfer learning (TL) is widely used in conventional hybrid automatic speech recognition (ASR) system, to transfer the knowledge from source to target language. TL can be applied to end-to-end (E2E) ASR system such as recurrent neural…

Simultaneous or streaming machine translation generates translation while reading the input stream. These systems face a quality/latency trade-off, aiming to achieve high translation quality similar to non-streaming models with minimal…

In online learning from non-stationary data streams, it is necessary to learn robustly to outliers and to adapt quickly to changes in the underlying data generating mechanism. In this paper, we refer to the former attribute of online…

With the increased audiovisualisation of communication, the need for live subtitles in multilingual events is more relevant than ever. In an attempt to automatise the process, we aim at exploring the feasibility of simultaneous speech…

Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…

In this paper, online linear regression in environments corrupted by non-Gaussian noise (especially heavy-tailed noise) is addressed. In such environments, the error between the system output and the label also does not follow a Gaussian…

End-to-end speech-to-speech translation (S2ST) without relying on intermediate text representations is a rapidly emerging frontier of research. Recent works have demonstrated that the performance of such direct S2ST systems is approaching…

It has been known that direct speech-to-speech translation (S2ST) models usually suffer from the data scarcity issue because of the limited existing parallel materials for both source and target speech. Therefore to train a direct S2ST…

Pre-training and fine-tuning is a paradigm for alleviating the data scarcity problem in end-to-end speech translation (E2E ST). The commonplace "modality gap" between speech and text data often leads to inconsistent inputs between…

Text-only adaptation of an end-to-end (E2E) model remains a challenging task for automatic speech recognition (ASR). Language model (LM) fusion-based approaches require an additional external LM during inference, significantly increasing…

Simultaneous translation, which starts translating each sentence after receiving only a few words in source sentence, has a vital role in many scenarios. Although the previous prefix-to-prefix framework is considered suitable for…

Reinforcement Learning (RL) has become an effective paradigm for enhancing Large Language Models (LLMs) and visual generative models. However, its application in text-to-audio (TTA) generation remains largely under-explored. Prior work…

Speech Large Language Models have achieved breakthroughs in multilingual speech-to-text translation. However, existing approaches often overlook semantic commonalities across source languages, leading to biased translation performance. In…

Speech-to-text translation (ST) is a cross-modal task that involves converting spoken language into text in a different language. Previous research primarily focused on enhancing speech translation by facilitating knowledge transfer from…

This paper introduces a cross-lingual dubbing system that translates speech from one language to another while preserving key characteristics such as duration, speaker identity, and speaking speed. Despite the strong translation quality of…

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Test-Time Adaptation (TTA) has emerged as an effective solution for adapting Vision Transformers (ViT) to distribution shifts without additional training data. However, existing TTA methods often incur substantial computational overhead,…

Streaming speech-to-text translation (StreamST) is the task of automatically translating speech while incrementally receiving an audio stream. Unlike simultaneous ST (SimulST), which deals with pre-segmented speech, StreamST faces the…

Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models…