Dan Su

Dan Su

Auto-generated profile, based on publicly available information

Dan Su

Tencent AI Lab Tencent Shenzhen China

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 March 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
ZJZiwei Ji
Ziwei Ji
NLNayeon Lee
Nayeon Lee
RFRita Frieske
Rita Frieske
TYTiezheng Yu
Tiezheng Yu
DSDan Su
Dan Su
PFPascale Fung
Pascale Fung
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation, and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before.In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions, and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.

1 January 2019
Verified
Conference Paper
Open access
PDF file
DSDan Su
Dan Su
YXYan Xu
Yan Xu
GWGenta Indra Winata
Genta Indra Winata
PXPeng Xu
Peng Xu
HKHyeondey Kim
Hyeondey Kim
PFPascale Fung
Pascale Fung
Dan Su, Yan Xu, Genta Indra Winata, Peng Xu, Hyeondey Kim, Zihan Liu, Pascale Fung. Proceedings of the 2nd Workshop on Machine Reading for Question Answering. 2019.

1 May 2020 in Neural Networks
Verified
Journal Article
Closed access
SYShan Yang
Shan Yang
HLHeng Lu
Heng Lu
SKShiyin Kang
Shiyin Kang
LXLiumeng Xue
Liumeng Xue
JXJinba Xiao
Jinba Xiao
DYDong Yu
Dong Yu

1 May 2020
Verified
Conference Paper
Closed access
XJXuan Ji
Xuan Ji
MYMeng Yu
Meng Yu
CZChunlei Zhang
Chunlei Zhang
DSDan Su
Dan Su
TYTao Yu
Tao Yu
DYDong Yu
Dong Yu
Deep learning based speech separation approaches have received great interest, among which the recent speaker-aware speech enhancement methods are promising for solving difficulties such as arbitrary source permutation and unknown number of sources. In this paper, we propose a novel training framework which jointly learns the speaker-conditioned target speaker extraction model and its associated speaker embedding model. The resulting unified model directly learns the appropriate speaker embedding for improved target speech enhancement. We demonstrate, on our large simulated noisy and far-field evaluation sets of overlapped speech signals, that our proposed approach significantly improves the speech enhancement performance compared to the baseline speaker-aware speech enhancement models.

1 May 2020
Verified
Conference Paper
Closed access
SLSongxiang Liu
Songxiang Liu
DWDisong Wang
Disong Wang
YCYuewen Cao
Yuewen Cao
LSLifa Sun
Lifa Sun
XWXixin Wu
Xixin Wu
HMHelen Meng
Helen Meng
Techniques for accent conversion (AC) aim to convert non-native to native accented speech. Conventional AC methods try to convert only the speaker identity of a native speaker’s voice to that of the non-native accented target speaker, leaving the underlying content and pronunciations unchanged. This hinders their practical use in real-world applications, because native-accented utterances are required at conversion stage. In this paper, we present an end-to-end framework, which is able to conduct AC from non-native-accented utterances without using any native-accented utterances during online conversion. We achieve this by independently extracting linguistic and speaker representations from non-native accented speech and condition a speech synthesis model on these representations to generate native-accented speech. Experiments on open-source data corpora show that the proposed system can convert Hindi-accented English speech into native American English speech with high naturalness, which is indistinguishable from native-accented recordings in terms of accent.

2 November 2012
Verified
Conference Paper
Open access
PDF file
DSDan Su
Dan Su
PFPascale Fung
Pascale Fung