no code implementations • ACL (IWSLT) 2021 • Danni Liu, Jan Niehues
The task in this track is to build multilingual speech translation systems in supervised and zero-shot directions.
no code implementations • WMT (EMNLP) 2021 • Danni Liu, Jan Niehues
We present our development of the multilingual machine translation system for the large-scale multilingual machine translation task at WMT 2021.
no code implementations • IWSLT (ACL) 2022 • Ngoc-Quan Pham, Tuan Nam Nguyen, Thai-Binh Nguyen, Danni Liu, Carlos Mullov, Jan Niehues, Alexander Waibel
Pretrained models in acoustic and textual modalities can potentially improve speech translation for both Cascade and End-to-end approaches.
no code implementations • 8 Apr 2024 • Vladimir Solovyev, Danni Liu, Jan Niehues
In this work, we focus on summarization and tackle the problem through the lens of language-independent representations.
1 code implementation • 15 Sep 2023 • Danni Liu, Jan Niehues
This gap is out of sync with recent progress in pretrained massively multilingual translation models.
no code implementations • 7 Aug 2023 • Christian Huber, Tu Anh Dinh, Carlos Mullov, Ngoc Quan Pham, Thai Binh Nguyen, Fabian Retkowski, Stefan Constantin, Enes Yavuz Ugan, Danni Liu, Zhaolin Li, Sai Koneru, Jan Niehues, Alexander Waibel
Secondly, we compare different approaches to low-latency speech translation using this framework.
1 code implementation • 8 Jun 2023 • Danni Liu, Thai Binh Nguyen, Sai Koneru, Enes Yavuz Ugan, Ngoc-Quan Pham, Tuan-Nam Nguyen, Tu Anh Dinh, Carlos Mullov, Alexander Waibel, Jan Niehues
In this paper, we describe our speech translation system for the multilingual track of IWSLT 2023, which evaluates translation quality on scientific conference talks.
1 code implementation • 2 Nov 2022 • Danni Liu, Jan Niehues
In this work, we discretize the encoder output latent space of multilingual models by assigning encoder states to entries in a codebook, which in effect represents source sentences in a new artificial language.
no code implementations • IWSLT (ACL) 2022 • Peter Polák, Ngoc-Quan Ngoc, Tuan-Nam Nguyen, Danni Liu, Carlos Mullov, Jan Niehues, Ondřej Bojar, Alexander Waibel
In this paper, we describe our submission to the Simultaneous Speech Translation at IWSLT 2022.
1 code implementation • 26 Jan 2022 • Tu Anh Dinh, Danni Liu, Jan Niehues
We investigate whether these ideas can be applied to speech translation, by building ST models trained on speech transcription and text translation data.
no code implementations • 14 Jan 2022 • Sai Koneru, Danni Liu, Jan Niehues
Although AL is shown to be helpful with large budgets, it is not enough to build high-quality translation systems in these low-resource conditions.
no code implementations • 15 Oct 2021 • Xutai Ma, Hongyu Gong, Danni Liu, Ann Lee, Yun Tang, Peng-Jen Chen, Wei-Ning Hsu, Phillip Koehn, Juan Pino
We present a direct simultaneous speech-to-speech translation (Simul-S2ST) model, Furthermore, the generation of translation is independent from intermediate text representations.
no code implementations • 15 Oct 2021 • Danni Liu, Changhan Wang, Hongyu Gong, Xutai Ma, Yun Tang, Juan Pino
Speech-to-speech translation (S2ST) converts input speech to speech in another language.
no code implementations • EACL (DravidianLangTech) 2021 • Sai Koneru, Danni Liu, Jan Niehues
We show that unifying the writing systems is essential in unsupervised translation between the Dravidian languages.
1 code implementation • ACL 2021 • Danni Liu, Jan Niehues, James Cross, Francisco Guzmán, Xian Li
The difficulty of generalizing to new translation directions suggests the model representations are highly specific to those language pairs seen in training.
1 code implementation • WS 2020 • Danni Liu, Jan Niehues, Gerasimos Spanakis
The experiments show that with limited data far less than needed for training a model from scratch, we can adapt a Transformer-based ASR model to incorporate both transcription and compression capabilities.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 22 May 2020 • Danni Liu, Gerasimos Spanakis, Jan Niehues
On How2 English-Portuguese speech translation, we reduce latency to 0. 7 second (-84% rel.)
Sequence-To-Sequence Speech Recognition speech-recognition +1