Shansong Liu

676 total citations
31 papers, 432 citations indexed

About

Shansong Liu is a scholar working on Artificial Intelligence, Signal Processing and Physiology. According to data from OpenAlex, Shansong Liu has authored 31 papers receiving a total of 432 indexed citations (citations by other indexed papers that have themselves been cited), including 25 papers in Artificial Intelligence, 22 papers in Signal Processing and 7 papers in Physiology. Recurrent topics in Shansong Liu's work include Speech Recognition and Synthesis (22 papers), Speech and Audio Processing (16 papers) and Music and Audio Processing (16 papers). Shansong Liu is often cited by papers focused on Speech Recognition and Synthesis (22 papers), Speech and Audio Processing (16 papers) and Music and Audio Processing (16 papers). Shansong Liu collaborates with scholars based in China, Hong Kong and United States. Shansong Liu's co-authors include Xunying Liu, Helen Meng, Jianwei Yu, Shoukang Hu, Mengzhe Geng, Xurong Xie, Shi-Xiong Zhang, Max W. Y. Lam, Zi Ye and Bo Wu and has published in prestigious journals such as Proceedings of the IEEE, Expert Systems with Applications and IEEE/ACM Transactions on Audio Speech and Language Processing.

In The Last Decade

Shansong Liu

28 papers receiving 412 citations

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Shansong Liu China	12	331	255	182	99	29	31	432
Mengzhe Geng Hong Kong	12	313 0.9×	193 0.8×	214 1.2×	122 1.2×	24 0.8×	37	407
Keigo Nakamura Japan	12	397 1.2×	385 1.5×	137 0.8×	55 0.6×	23 0.8×	23	463
Miloš Cerňak Switzerland	14	365 1.1×	282 1.1×	85 0.5×	125 1.3×	63 2.2×	61	487
Bajibabu Bollepalli Finland	8	225 0.7×	188 0.7×	39 0.2×	59 0.6×	21 0.7×	24	282
Xurong Xie China	9	217 0.7×	160 0.6×	117 0.6×	75 0.8×	13 0.4×	35	272
Tamás Gábor Csapó Hungary	11	249 0.8×	211 0.8×	41 0.2×	56 0.6×	33 1.1×	62	347
Ravichander Vipperla France	11	272 0.8×	224 0.9×	38 0.2×	37 0.4×	41 1.4×	23	348
Phani Sankar Nidadavolu United States	10	198 0.6×	174 0.7×	70 0.4×	27 0.3×	36 1.2×	16	295
Lauri Juvela Finland	12	321 1.0×	347 1.4×	43 0.2×	50 0.5×	64 2.2×	36	406
Wen-Chin Huang Japan	13	426 1.3×	355 1.4×	65 0.4×	51 0.5×	33 1.1×	38	508

Countries citing papers authored by Shansong Liu

Since Specialization

Citations

This map shows the geographic impact of Shansong Liu's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Shansong Liu with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Shansong Liu more than expected).

Fields of papers citing papers by Shansong Liu

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Shansong Liu. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Shansong Liu. The network helps show where Shansong Liu may publish in the future.

Co-authorship network of co-authors of Shansong Liu

This figure shows the co-authorship network connecting the top 25 collaborators of Shansong Liu. A scholar is included among the top collaborators of Shansong Liu based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Shansong Liu. Shansong Liu is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

Liu, Shansong, et al.. (2025). MuMu-LLaMA: Multi-modal music understanding and generation via large language models. Expert Systems with Applications. 305. 130688–130688.

Hou, Siyuan, et al.. (2025). Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 1–5.

Liu, Shansong, et al.. (2024). Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning. 286–290. 8 indexed citations

Yang, Zhihan, et al.. (2023). Prosody Modeling with 3D Visual Information for Expressive Video Dubbing. 4863–4867. 1 indexed citations

Hu, Shoukang, Shansong Liu, Jianwei Yu, et al.. (2022). Neural Architecture Search for LF-MMI Trained Time Delay Neural Networks. IEEE/ACM Transactions on Audio Speech and Language Processing. 30. 1093–1107. 11 indexed citations

Hu, Shujie, Shansong Liu, Xurong Xie, et al.. (2022). Exploiting Cross Domain Acoustic-to-Articulatory Inverted Features for Disordered Speech Recognition. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 6747–6751. 8 indexed citations

Liu, Shansong, Mengzhe Geng, Shoukang Hu, et al.. (2021). Recent Progress in the CUHK Dysarthric Speech Recognition System. IEEE/ACM Transactions on Audio Speech and Language Processing. 29. 2267–2281. 57 indexed citations

Hu, Shoukang, Mengzhe Geng, Zi Ye, et al.. (2021). Bayesian Parametric and Architectural Domain Adaptation of LF-MMI Trained TDNNs for Elderly and Dysarthric Speech Recognition. 4818–4822. 7 indexed citations

Hu, Shoukang, et al.. (2021). Neural Architecture Search for LF-MMI Trained Time Delay Neural Networks. 6758–6762. 6 indexed citations

10.

Geng, Mengzhe, Shansong Liu, Jianwei Yu, et al.. (2021). Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition. arXiv (Cornell University). 4793–4797. 15 indexed citations

11.

Yu, Jianwei, Shansong Liu, Shoukang Hu, et al.. (2021). Bayesian Transformer Language Models for Speech Recognition. 7378–7382. 11 indexed citations

12.

Ye, Zi, Shoukang Hu, Mengzhe Geng, et al.. (2021). Development of the Cuhk Elderly Speech Recognition System for Neurocognitive Disorder Detection Using the Dementiabank Corpus. 6433–6437. 24 indexed citations

13.

Geng, Mengzhe, et al.. (2021). Adversarial Data Augmentation for Disordered Speech Recognition. 4803–4807. 25 indexed citations

14.

Liu, Shansong, Xurong Xie, Jianwei Yu, et al.. (2020). Exploiting Cross-Domain Visual Feature Generation for Disordered Speech Recognition. 711–715. 15 indexed citations

15.

Yu, Jianwei, Shi-Xiong Zhang, Jian Wu, et al.. (2020). Audio-Visual Recognition of Overlapped Speech for the LRS2 Dataset. 6984–6988. 53 indexed citations

16.

Hu, Shoukang, Shansong Liu, Heng Chang, et al.. (2019). The CUHK Dysarthric Speech Recognition Systems for English and Cantonese.. Conference of the International Speech Communication Association. 3669–3670. 11 indexed citations

17.

Liu, Shansong, Shoukang Hu, Xunying Liu, & Helen Meng. (2019). On the Use of Pitch Features for Disordered Speech Recognition. 4130–4134. 12 indexed citations

18.

Liu, Shansong, et al.. (2019). Exploiting Visual Features Using Bayesian Gated Neural Networks for Disordered Speech Recognition. 4120–4124. 15 indexed citations

19.

Liu, Xunying, Shansong Liu, Jianwei Yu, et al.. (2018). Limited-Memory BFGS Optimization of Recurrent Neural Network Language Models for Speech Recognition. 6114–6118. 7 indexed citations

20.

Lam, Max W. Y., Shoukang Hu, Xurong Xie, et al.. (2018). Gaussian Process Neural Networks for Speech Recognition. 1778–1782. 8 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact