Výsledky vyhledávání

Report

NAIST Simultaneous Speech Translation System for IWSLT 2024

Autor: Ko, Yuka, Fukuda, Ryo, Nishikawa, Yuta, Kano, Yasumasa, Yanagita, Tomoya, Doi, Kosuke, Makinae, Mana, Tan, Haotian, Sakai, Makoto, Sakti, Sakriani, Sudoh, Katsuhito, Nakamura, Satoshi

This paper describes NAIST's submission to the simultaneous track of the IWSLT 2024 Evaluation Campaign: English-to-{German, Japanese, Chinese} speech-to-text translation and English-to-Japanese speech-to-speech translation. We develop a multilingual

Externí odkaz: http://arxiv.org/abs/2407.00826

Zobrazit plný text záznamu

Report

Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data

Autor: Ko, Yuka, Fukuda, Ryo, Nishikawa, Yuta, Kano, Yasumasa, Sudoh, Katsuhito, Nakamura, Satoshi

Simultaneous speech translation (SimulST) translates partial speech inputs incrementally. Although the monotonic correspondence between input and output is preferable for smaller latency, it is not the case for distant language pairs such as English

Externí odkaz: http://arxiv.org/abs/2306.08582

Zobrazit plný text záznamu

Report

Improving Speech Translation Accuracy and Time Efficiency with Fine-tuned wav2vec 2.0-based Speech Segmentation

Autor: Fukuda, Ryo, Sudoh, Katsuhito, Nakamura, Satoshi

Speech translation (ST) automatically converts utterances in a source language into text in another language. Splitting continuous speech into shorter segments, known as speech segmentation, plays an important role in ST. Recent segmentation methods

Externí odkaz: http://arxiv.org/abs/2304.12659

Zobrazit plný text záznamu

Report

NAIST-SIC-Aligned: an Aligned English-Japanese Simultaneous Interpretation Corpus

Autor: Zhao, Jinming, Ko, Yuka, Doi, Kosuke, Fukuda, Ryo, Sudoh, Katsuhito, Nakamura, Satoshi

It remains a question that how simultaneous interpretation (SI) data affects simultaneous machine translation (SiMT). Research has been limited due to the lack of a large-scale training corpus. In this work, we aim to fill in the gap by introducing N

Externí odkaz: http://arxiv.org/abs/2304.11766

Zobrazit plný text záznamu

Report

Speech Segmentation Optimization using Segmented Bilingual Speech Corpus for End-to-end Speech Translation

Autor: Fukuda, Ryo, Sudoh, Katsuhito, Nakamura, Satoshi

Speech segmentation, which splits long speech into short segments, is essential for speech translation (ST). Popular VAD tools like WebRTC VAD have generally relied on pause-based segmentation. Unfortunately, pauses in speech do not necessarily match

Externí odkaz: http://arxiv.org/abs/2203.15479

Zobrazit plný text záznamu