Related papers: NAIST Simultaneous Speech Translation System for I…

We present a direct simultaneous speech-to-speech translation (Simul-S2ST) model, Furthermore, the generation of translation is independent from intermediate text representations. Our approach leverages recent progress on direct…

Current end-to-end approaches to Spoken Language Translation (SLT) rely on limited training resources, especially for multilingual settings. On the other hand, Multilingual Neural Machine Translation (MultiNMT) approaches rely on…

A rising interest in the modality extension of foundation language models warrants discussion on the most effective, and efficient, multimodal training approach. This work focuses on neural machine translation (NMT) and proposes a joint…

We propose a new model architecture specifically suited for text-to-speech (TTS) models. We combine WavLM, a pre-trained self-supervised learning (SSL) speech model, and the BEST-RQ vector quantization framework. We assess the extent to…

In speech translation, leveraging multimodal data to improve model performance and address limitations of individual modalities has shown significant effectiveness. In this paper, we harness the complementary strengths of speech and text,…

Simultaneous speech translation (SST) takes streaming speech input and generates text translation on the fly. Existing methods either have high latency due to recomputation of input representations, or fall behind of offline ST in…

We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of…

This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…

Current Text-to-Speech models pose a multilingual challenge, where most of the models traditionally focus on English and European languages, thereby hurting the potential to provide access to information to many more people. To address this…

Simultaneous translation of unbounded streaming speech remains a challenging problem due to the need for effectively processing the history speech context and past translations so that quality and latency, including computation overhead,…

Direct speech-to-speech translation (S2ST) has achieved impressive translation quality, but it often faces the challenge of slow decoding due to the considerable length of speech sequences. Recently, some research has turned to…

We present a multi-speaker Japanese audiobook text-to-speech (TTS) system that leverages multimodal context information of preceding acoustic context and bilateral textual context to improve the prosody of synthetic speech. Previous work…

This paper describes our system submission to the International Conference on Spoken Language Translation (IWSLT 2024) for Irish-to-English speech translation. We built end-to-end systems based on Whisper, and employed a number of data…

We propose a novel approach to significantly improve the intelligibility in the Non-Audible Murmur (NAM)-to-speech conversion task, leveraging self-supervision and sequence-to-sequence (Seq2Seq) learning techniques. Unlike conventional…

We present a framework for building speech-to-text translation (ST) systems using only monolingual speech and text corpora, in other words, speech utterances from a source language and independent text from a target language. As opposed to…

We present ParrotTTS, a modularized text-to-speech synthesis model leveraging disentangled self-supervised speech representations. It can train a multi-speaker variant effectively using transcripts from a single speaker. ParrotTTS adapts to…

Most of the existing Neural Machine Translation (NMT) models focus on the conversion of sequential data and do not directly use syntactic information. We propose a novel end-to-end syntactic NMT model, extending a sequence-to-sequence model…

We address the problem of cross-speaker style transfer for text-to-speech (TTS) using data augmentation via voice conversion. We assume to have a corpus of neutral non-expressive data from a target speaker and supporting conversational…

This paper describes the University of Sydney& JD's joint submission of the IWSLT 2021 low resource speech translation task. We participated in the Swahili-English direction and got the best scareBLEU (25.3) score among all the…

Many recently published Text-to-Speech (TTS) systems produce audio close to real speech. However, TTS evaluation needs to be revisited to make sense of the results obtained with the new architectures, approaches and datasets. We propose…