The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

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 …

How can speech-to-text translation (ST) perform as well as machine translation (MT)? The
key point is to bridge the modality gap between speech and text so that useful MT …

We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech
translations mined from real speech of European Parliament recordings. It contains speech …

The success of end-to-end speech-to-text translation (ST) is often achieved by utilizing
source transcripts, eg, by pre-training with automatic speech recognition (ASR) and machine …

Speech-to-speech translation (S2ST) enables spoken communication between people
talking in different languages. Despite a few studies on multilingual S2ST, their focus is the …

Recently proposed two-pass direct speech-to-speech translation (S2ST) models decompose
the task into speech-to-text translation (S2TT) and text-to-speech (TTS) within an end-to-end …

Speech-to-speech translation (S2ST), particularly in the context of low-resource languages,
plays a vital role in facilitating global communication. However, comprehensive research in …

Dysarthric speech reconstruction (DSR) systems aim to automatically convert dysarthric
speech into normal-sounding speech. The technology eases communication with speakers …

Although there has been significant advancement in the field of speech-to-speech
translation, conventional models still require language-parallel speech data between the …