Zobrazeno 1 - 10
of 92
pro vyhledávání: '"Gao, Yingbo"'
In this paper, alternating weak triphone/BPE alignment supervision is proposed to improve end-to-end model training. Towards this end, triphone and BPE alignments are extracted using a pre-existing hybrid ASR system. Then, regularization effect is ob
Externí odkaz:
http://arxiv.org/abs/2402.15594
In this paper, we aim to create weak alignment supervision from an existing hybrid system to aid the end-to-end modeling of automatic speech recognition. Towards this end, we use the existing hybrid ASR system to produce triphone alignments of the tr
Externí odkaz:
http://arxiv.org/abs/2311.14835
The integration of language models for neural machine translation has been extensively studied in the past. It has been shown that an external language model, trained on additional target-side monolingual data, can help improve translation quality. H
Externí odkaz:
http://arxiv.org/abs/2306.05077
Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results. However, fundamental challenges such as error propagation from the automatic speech recogni
Externí odkaz:
http://arxiv.org/abs/2210.13700
Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. For machine translation, despite the evolution from long short-term memory networks to Transformer networks, plus the introduction and development of attention me
Externí odkaz:
http://arxiv.org/abs/2210.11807
Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. The calculation is cheap to perform and the fact that the translation improvement almost comes for free, makes it widely ad
Externí odkaz:
http://arxiv.org/abs/2210.11803
Autor:
Yang, Zijian, Gao, Yingbo, Gerstenberger, Alexander, Jiang, Jintao, Schlüter, Ralf, Ney, Hermann
To mitigate the problem of having to traverse over the full vocabulary in the softmax normalization of a neural language model, sampling-based training criteria are proposed and investigated in the context of large vocabulary word-based neural langua
Externí odkaz:
http://arxiv.org/abs/2111.06310
Autor:
Gao, Yingbo, Thulke, David, Gerstenberger, Alexander, Tran, Khoa Viet, Schlüter, Ralf, Ney, Hermann
As the vocabulary size of modern word-based language models becomes ever larger, many sampling-based training criteria are proposed and investigated. The essence of these sampling methods is that the softmax-related traversal over the entire vocabula
Externí odkaz:
http://arxiv.org/abs/2104.10507
Autor:
Gao, Yingbo, Liu, Chang, Wang, Junpeng, Lv, Minjia, Liu, Xin, Zhang, Xiaoxiang, Zhou, Juan, Li, Xiangbo, Wang, Yulong, Dong, Guichun, Huang, Jianye, Liang, Guohua, Yang, Zefeng, Zhou, Yong, Yao, Youli
Publikováno v:
In Field Crops Research 1 February 2024 306
Autor:
Huo, Jingjing, Herold, Christian, Gao, Yingbo, Dahlmann, Leonard, Khadivi, Shahram, Ney, Hermann
Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various architectur
Externí odkaz:
http://arxiv.org/abs/2010.09482