Transvip: Speech To Speech Translation System With Voice And Isochrony Preservation

Abstract

There is a rising interest and trend in research towards directly translating speech from one language to another, known as end-to-end speech-to-speech translation. However, most end-to-end models struggle to outperform cascade models, i.e., a pipeline framework by concatenating speech recognition, machine translation and text-to-speech models. The primary challenges stem from the inherent complexities involved in direct translation tasks and the scarcity of data. In this study, we introduce a novel model framework TransVIP that leverages diverse datasets in a cascade fashion yet facilitates end-to-end inference through joint probability. Furthermore, we propose two separated encoders to preserve the speaker's voice characteristics and isochrony from the source speech during the translation process, making it highly suitable for scenarios such as video dubbing. Our experiments on the French-English language pair demonstrate that our model outperforms the current state-of-the-art speech

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyle2024transvip

Related papers

• Translatotron 2: High-quality Direct Speech-to-speech Translation With Voice Preservation (2021)0.00
• Crossvoice: Crosslingual Prosody Preserving Cascade-s2st Using Transfer Learning (2024)0.00
• Speech Translation And The End-to-end Promise: Taking Stock Of Where We Are (2020)11.93
• Transface: Unit-based Audio-visual Speech Synthesizer For Talking Head Translation (2023)7.16
• Synchronous Speech Recognition And Speech-to-text Translation With Interactive Decoding (2019)10.48
• Tight Integrated End-to-end Training For Cascaded Speech Translation (2020)8.35
• Isochrony-controlled Speech-to-text Translation: A Study On Translating From Sino-tibetan To Indo-european Languages (2024)0.00
• Leveraging Unsupervised And Weakly-supervised Data To Improve Direct Speech-to-speech Translation (2022)8.35