Related papers: DUB: Discrete Unit Back-translation for Speech Tra…
Simultaneous speech translation (SST) produces target text incrementally from partial speech input. Recent speech large language models (Speech LLMs) have substantially improved SST quality, yet they still struggle to correctly translate…
Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…
This paper proposes a direct text to speech translation system using discrete acoustic units. This framework employs text in different source languages as input to generate speech in the target language without the need for text…
The success of building textless speech-to-speech translation (S2ST) models has attracted much attention. However, S2ST still faces two main challenges: 1) extracting linguistic features for various speech signals, called cross-modal (CM),…
This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). This work aims to build a single multilingual translation system with a…
Direct speech-to-speech translation (S2ST) translates speech from one language into another using a single model. However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal…
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite…
Recently, representation learning for text and speech has successfully improved many language related tasks. However, all existing methods suffer from two limitations: (a) they only learn from one input modality, while a unified…
This paper proposes a textless training method for many-to-many multilingual speech-to-speech translation that can also benefit the transfer of pre-trained knowledge to text-based systems, text-to-speech synthesis and text-to-speech…
Given the great success of large language models (LLMs) across various tasks, in this paper, we introduce LLM-ST, a novel and effective speech translation model constructed upon a pre-trained LLM. By integrating the large language model…
The rapid development of single-modal pre-training has prompted researchers to pay more attention to cross-modal pre-training methods. In this paper, we propose a unified-modal speech-unit-text pre-training model, SpeechUT, to connect the…
To alleviate the data scarcity problem in End-to-end speech translation (ST), pre-training on data for speech recognition and machine translation is considered as an important technique. However, the modality gap between speech and text…
Speech-to-speech translation (S2ST) has been advanced with large language models (LLMs), which are fine-tuned on discrete speech units. In such approaches, modality adaptation from text to speech has been an issue. LLMs are trained on…
Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. One of these methods is…
The paper describes the BUT's speech translation systems. The systems are English$\longrightarrow$German offline speech translation systems. The systems are based on our previous works \cite{Jointly_trained_transformers}. Though End-to-End…
End-to-end simultaneous speech translation (SST), which directly translates speech in one language into text in another language in real-time, is useful in many scenarios but has not been fully investigated. In this work, we propose…
Previous studies demonstrated that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST). However, they required a dedicated model for phone recognition and did not test this solution for direct…
End-to-End Speech Translation (E2E-ST) is the task of translating source speech directly into target text bypassing the intermediate transcription step. The representation discrepancy between the speech and text modalities has motivated…
Recent advancements in large language models (LLMs) have demonstrated their remarkable capabilities across various language tasks. Inspired by the success of text-to-text translation refinement, this paper investigates how LLMs can improve…
Neural transducers have been widely used in automatic speech recognition (ASR). In this paper, we introduce it to streaming end-to-end speech translation (ST), which aims to convert audio signals to texts in other languages directly.…