The paper presents the HW-TSC’s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022.
This paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task.
This paper presents the submission of Huawei Translation Services Center (HW-TSC) to the WMT 2021 Large-Scale Multilingual Translation Task.
This paper presents the submission of Huawei Translation Services Center (HW-TSC) to WMT 2021 Efficiency Shared Task.
This paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC).
Compared with the commonly used NuQE baseline, BAL-QE achieves 47% (En-Ru) and 75% (En-De) of performance promotions.
We propose a unified multilingual model for humor detection which can be trained under a transfer learning framework.
This paper describes our work in the WAT 2020 Indic Multilingual Translation Task.
This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT 2021 News Translation Shared Task.
This paper presents our submissions to the IWSLT 2022 Isometric Spoken Language Translation task.
We also conduct experiment with similar language augmentation, which lead to positive results, although not used in our submission.
The paper presents the submission by HW-TSC in the WMT 2020 Automatic Post Editing Shared Task.
For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora.
This paper presents our work in the WMT 2020 Word and Sentence-Level Post-Editing Quality Estimation (QE) Shared Task.
The cascade system is composed of a chunking-based streaming ASR model and the SimulMT model used in the T2T track.
Child speech, as a representative type of low-resource speech, is leveraged for adaptation.
BERTScore is an effective and robust automatic metric for referencebased machine translation evaluation.
To boost the performance of vision Transformers on small datasets, this paper proposes to explicitly increase the input information density in the frequency domain.
The emotion encoder extracts the identity of emotion type as well as the respective emotion intensity from the mel-spectrogram of input speech.
To this end, we propose a plug-in algorithm for this line of work, i. e., Aligned Constrained Training (ACT), which alleviates this problem by familiarizing the model with the source-side context of the constraints.
However, in terms of ultimately achieved system performance for target speaker(s), the actual benefits of model pre-training are uncertain and unstable, depending very much on the quantity and text content of training data.
Input to these classifiers are speech transcripts produced by automatic speech recognition (ASR) models.
This paper describes our work in participation of the IWSLT-2021 offline speech translation task.
This paper describes a novel design of a neural network-based speech generation model for learning prosodic representation. The problem of representation learning is formulated according to the information bottleneck (IB) principle.
The paper presents details of our system in the IWSLT Video Speech Translation evaluation.