Related papers: Average Token Delay: A Latency Metric for Simultan…
Although measuring intrinsic quality has been a key factor in the advancement of Machine Translation (MT), successfully deploying MT requires considering not just intrinsic quality but also the user experience, including aspects such as…
Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to…
Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…
Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…
End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research. However, data sparsity limits the performance of…
Learning target side syntactic structure has been shown to improve Neural Machine Translation (NMT). However, incorporating syntax through latent variables introduces additional complexity in inference, as the models need to marginalize…
Speech enhancement models should meet very low latency requirements typically smaller than 5 ms for hearing assistive devices. While various low-latency techniques have been proposed, comparing these methods in a controlled setup using DNNs…
Alignment with human preferences is an important step in developing accurate and safe large language models. This is no exception in machine translation (MT), where better handling of language nuances and context-specific variations leads…
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…
One of the major impediments to the development of new task-oriented dialogue (TOD) systems is the need for human evaluation at multiple stages and iterations of the development process. In an effort to move toward automated evaluation of…
Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specific projects. Machine translation (MT) has achieved…
Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding. However, our research indicates that token-level alignment is also…
The rapid development of large pretrained language models has revolutionized not only the field of Natural Language Generation (NLG) but also its evaluation. Inspired by the recent work of BARTScore: a metric leveraging the BART language…
Large language models (LLMs) are typically developed through large-scale pre-training followed by task-specific fine-tuning. Recent advances highlight the importance of an intermediate mid-training stage, where models undergo multiple…
While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…
Simultaneous Interpretation (SI) represents one of the most daunting frontiers in the translation industry, with product-level automatic systems long plagued by intractable challenges: subpar transcription and translation quality, lack of…
Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…
As research on machine translation moves to translating text beyond the sentence level, it remains unclear how effective automatic evaluation metrics are at scoring longer translations. In this work, we first propose a method for creating…
Modern machine translation (MT) systems depend on large parallel corpora, often collected from the Internet. However, recent evidence indicates that (i) a substantial portion of these texts are machine-generated translations, and (ii) an…
Recent advancements in text-to-speech (TTS) systems, such as FastSpeech and StyleSpeech, have significantly improved speech generation quality. However, these models often rely on duration generated by external tools like the Montreal…