English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper describes the NPU-MSXF system for the IWSLT 2023 speech-to-speechtranslation (S2ST) task which aims to translate from English speech ofmulti-source to Chinese speech. The system is built in a cascaded mannerconsisting of automatic speech recognition (ASR), machine translation (MT), andtext-to-speech (TTS). We make tremendous efforts to handle the challengingmulti-source input. Specifically, to improve the robustness to multi-sourcespeech input, we adopt various data augmentation strategies and a ROVER-basedscore fusion on multiple ASR model outputs. To better handle the noisy ASRtranscripts, we introduce a three-stage fine-tuning strategy to improvetranslation accuracy. Finally, we build a TTS model with high naturalness andsound quality, which leverages a two-stage framework, using network bottleneckfeatures as a robust intermediate representation for speaker timbre andlinguistic content disentanglement. Based on the two-stage framework,pre-trained speaker embedding is leveraged as a condition to transfer thespeaker timbre in the source English speech to the translated Chinese speech.Experimental results show that our system has high translation accuracy, speechnaturalness, sound quality, and speaker similarity. Moreover, it shows goodrobustness to multi-source data.

The NPU-MSXF Speech-to-Speech Translation System for IWSLT 2023 Speech-to-Speech Translation Task